On the Beneficial Effects of Reinjections for Continual Learning
Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned d...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Solinas, Miguel [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| Übergeordnetes Werk: |
Enthalten in: SN Computer Science - Singapore : Springer Singapore, 2020, 4(2022), 1 vom: 01. Nov. |
|---|---|
| Übergeordnetes Werk: |
volume:4 ; year:2022 ; number:1 ; day:01 ; month:11 |
| Links: |
|---|
| DOI / URN: |
10.1007/s42979-022-01392-7 |
|---|
| Katalog-ID: |
SPR048514853 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR048514853 | ||
| 003 | DE-627 | ||
| 005 | 20230510060238.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 221102s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s42979-022-01392-7 |2 doi | |
| 035 | |a (DE-627)SPR048514853 | ||
| 035 | |a (SPR)s42979-022-01392-7-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Solinas, Miguel |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a On the Beneficial Effects of Reinjections for Continual Learning |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. | ||
| 650 | 4 | |a Incremental learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Lifelong learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Continual learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Sequential learning |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Pseudo-rehearsal |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Rehearsal |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Reyboz, Marina |0 (orcid)0000-0002-3373-2908 |4 aut | |
| 700 | 1 | |a Rousset, Stephane |4 aut | |
| 700 | 1 | |a Galliere, Julie |4 aut | |
| 700 | 1 | |a Mainsant, Marion |4 aut | |
| 700 | 1 | |a Bourrier, Yannick |4 aut | |
| 700 | 1 | |a Molnos, Anca |4 aut | |
| 700 | 1 | |a Mermillod, Martial |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t SN Computer Science |d Singapore : Springer Singapore, 2020 |g 4(2022), 1 vom: 01. Nov. |w (DE-627)1668832976 |w (DE-600)2977367-2 |x 2661-8907 |7 nnns |
| 773 | 1 | 8 | |g volume:4 |g year:2022 |g number:1 |g day:01 |g month:11 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s42979-022-01392-7 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 912 | |a GBV_ILN_11 | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_23 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_31 | ||
| 912 | |a GBV_ILN_32 | ||
| 912 | |a GBV_ILN_39 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_60 | ||
| 912 | |a GBV_ILN_62 | ||
| 912 | |a GBV_ILN_63 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_69 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_74 | ||
| 912 | |a GBV_ILN_90 | ||
| 912 | |a GBV_ILN_95 | ||
| 912 | |a GBV_ILN_100 | ||
| 912 | |a GBV_ILN_105 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_138 | ||
| 912 | |a GBV_ILN_150 | ||
| 912 | |a GBV_ILN_151 | ||
| 912 | |a GBV_ILN_152 | ||
| 912 | |a GBV_ILN_161 | ||
| 912 | |a GBV_ILN_170 | ||
| 912 | |a GBV_ILN_171 | ||
| 912 | |a GBV_ILN_187 | ||
| 912 | |a GBV_ILN_213 | ||
| 912 | |a GBV_ILN_224 | ||
| 912 | |a GBV_ILN_230 | ||
| 912 | |a GBV_ILN_250 | ||
| 912 | |a GBV_ILN_281 | ||
| 912 | |a GBV_ILN_285 | ||
| 912 | |a GBV_ILN_293 | ||
| 912 | |a GBV_ILN_370 | ||
| 912 | |a GBV_ILN_602 | ||
| 912 | |a GBV_ILN_636 | ||
| 912 | |a GBV_ILN_702 | ||
| 912 | |a GBV_ILN_2001 | ||
| 912 | |a GBV_ILN_2003 | ||
| 912 | |a GBV_ILN_2004 | ||
| 912 | |a GBV_ILN_2005 | ||
| 912 | |a GBV_ILN_2006 | ||
| 912 | |a GBV_ILN_2007 | ||
| 912 | |a GBV_ILN_2008 | ||
| 912 | |a GBV_ILN_2009 | ||
| 912 | |a GBV_ILN_2010 | ||
| 912 | |a GBV_ILN_2011 | ||
| 912 | |a GBV_ILN_2014 | ||
| 912 | |a GBV_ILN_2015 | ||
| 912 | |a GBV_ILN_2020 | ||
| 912 | |a GBV_ILN_2021 | ||
| 912 | |a GBV_ILN_2025 | ||
| 912 | |a GBV_ILN_2026 | ||
| 912 | |a GBV_ILN_2027 | ||
| 912 | |a GBV_ILN_2031 | ||
| 912 | |a GBV_ILN_2034 | ||
| 912 | |a GBV_ILN_2037 | ||
| 912 | |a GBV_ILN_2038 | ||
| 912 | |a GBV_ILN_2039 | ||
| 912 | |a GBV_ILN_2044 | ||
| 912 | |a GBV_ILN_2048 | ||
| 912 | |a GBV_ILN_2049 | ||
| 912 | |a GBV_ILN_2050 | ||
| 912 | |a GBV_ILN_2055 | ||
| 912 | |a GBV_ILN_2056 | ||
| 912 | |a GBV_ILN_2057 | ||
| 912 | |a GBV_ILN_2059 | ||
| 912 | |a GBV_ILN_2061 | ||
| 912 | |a GBV_ILN_2064 | ||
| 912 | |a GBV_ILN_2065 | ||
| 912 | |a GBV_ILN_2068 | ||
| 912 | |a GBV_ILN_2088 | ||
| 912 | |a GBV_ILN_2093 | ||
| 912 | |a GBV_ILN_2106 | ||
| 912 | |a GBV_ILN_2107 | ||
| 912 | |a GBV_ILN_2108 | ||
| 912 | |a GBV_ILN_2110 | ||
| 912 | |a GBV_ILN_2111 | ||
| 912 | |a GBV_ILN_2112 | ||
| 912 | |a GBV_ILN_2113 | ||
| 912 | |a GBV_ILN_2118 | ||
| 912 | |a GBV_ILN_2122 | ||
| 912 | |a GBV_ILN_2129 | ||
| 912 | |a GBV_ILN_2143 | ||
| 912 | |a GBV_ILN_2144 | ||
| 912 | |a GBV_ILN_2147 | ||
| 912 | |a GBV_ILN_2148 | ||
| 912 | |a GBV_ILN_2152 | ||
| 912 | |a GBV_ILN_2153 | ||
| 912 | |a GBV_ILN_2190 | ||
| 912 | |a GBV_ILN_2232 | ||
| 912 | |a GBV_ILN_2336 | ||
| 912 | |a GBV_ILN_2446 | ||
| 912 | |a GBV_ILN_2470 | ||
| 912 | |a GBV_ILN_2472 | ||
| 912 | |a GBV_ILN_2507 | ||
| 912 | |a GBV_ILN_2522 | ||
| 912 | |a GBV_ILN_4035 | ||
| 912 | |a GBV_ILN_4037 | ||
| 912 | |a GBV_ILN_4046 | ||
| 912 | |a GBV_ILN_4112 | ||
| 912 | |a GBV_ILN_4125 | ||
| 912 | |a GBV_ILN_4126 | ||
| 912 | |a GBV_ILN_4242 | ||
| 912 | |a GBV_ILN_4246 | ||
| 912 | |a GBV_ILN_4249 | ||
| 912 | |a GBV_ILN_4251 | ||
| 912 | |a GBV_ILN_4305 | ||
| 912 | |a GBV_ILN_4306 | ||
| 912 | |a GBV_ILN_4307 | ||
| 912 | |a GBV_ILN_4313 | ||
| 912 | |a GBV_ILN_4322 | ||
| 912 | |a GBV_ILN_4323 | ||
| 912 | |a GBV_ILN_4324 | ||
| 912 | |a GBV_ILN_4325 | ||
| 912 | |a GBV_ILN_4326 | ||
| 912 | |a GBV_ILN_4328 | ||
| 912 | |a GBV_ILN_4333 | ||
| 912 | |a GBV_ILN_4334 | ||
| 912 | |a GBV_ILN_4335 | ||
| 912 | |a GBV_ILN_4336 | ||
| 912 | |a GBV_ILN_4338 | ||
| 912 | |a GBV_ILN_4393 | ||
| 912 | |a GBV_ILN_4700 | ||
| 951 | |a AR | ||
| 952 | |d 4 |j 2022 |e 1 |b 01 |c 11 | ||
| author_variant |
m s ms m r mr s r sr j g jg m m mm y b yb a m am m m mm |
|---|---|
| matchkey_str |
article:26618907:2022----::nhbnfcaefcsfenetosocn |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s42979-022-01392-7 doi (DE-627)SPR048514853 (SPR)s42979-022-01392-7-e DE-627 ger DE-627 rakwb eng Solinas, Miguel verfasserin aut On the Beneficial Effects of Reinjections for Continual Learning 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. Incremental learning (dpeaa)DE-He213 Lifelong learning (dpeaa)DE-He213 Continual learning (dpeaa)DE-He213 Sequential learning (dpeaa)DE-He213 Pseudo-rehearsal (dpeaa)DE-He213 Rehearsal (dpeaa)DE-He213 Reyboz, Marina (orcid)0000-0002-3373-2908 aut Rousset, Stephane aut Galliere, Julie aut Mainsant, Marion aut Bourrier, Yannick aut Molnos, Anca aut Mermillod, Martial aut Enthalten in SN Computer Science Singapore : Springer Singapore, 2020 4(2022), 1 vom: 01. Nov. (DE-627)1668832976 (DE-600)2977367-2 2661-8907 nnns volume:4 year:2022 number:1 day:01 month:11 https://dx.doi.org/10.1007/s42979-022-01392-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_105 GBV_ILN_110 GBV_ILN_138 GBV_ILN_150 GBV_ILN_151 GBV_ILN_152 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_636 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2031 GBV_ILN_2034 GBV_ILN_2037 GBV_ILN_2038 GBV_ILN_2039 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2057 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2093 GBV_ILN_2106 GBV_ILN_2107 GBV_ILN_2108 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2144 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2446 GBV_ILN_2470 GBV_ILN_2472 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4246 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4328 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4336 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 AR 4 2022 1 01 11 |
| spelling |
10.1007/s42979-022-01392-7 doi (DE-627)SPR048514853 (SPR)s42979-022-01392-7-e DE-627 ger DE-627 rakwb eng Solinas, Miguel verfasserin aut On the Beneficial Effects of Reinjections for Continual Learning 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. Incremental learning (dpeaa)DE-He213 Lifelong learning (dpeaa)DE-He213 Continual learning (dpeaa)DE-He213 Sequential learning (dpeaa)DE-He213 Pseudo-rehearsal (dpeaa)DE-He213 Rehearsal (dpeaa)DE-He213 Reyboz, Marina (orcid)0000-0002-3373-2908 aut Rousset, Stephane aut Galliere, Julie aut Mainsant, Marion aut Bourrier, Yannick aut Molnos, Anca aut Mermillod, Martial aut Enthalten in SN Computer Science Singapore : Springer Singapore, 2020 4(2022), 1 vom: 01. Nov. (DE-627)1668832976 (DE-600)2977367-2 2661-8907 nnns volume:4 year:2022 number:1 day:01 month:11 https://dx.doi.org/10.1007/s42979-022-01392-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_105 GBV_ILN_110 GBV_ILN_138 GBV_ILN_150 GBV_ILN_151 GBV_ILN_152 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_636 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2031 GBV_ILN_2034 GBV_ILN_2037 GBV_ILN_2038 GBV_ILN_2039 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2057 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2093 GBV_ILN_2106 GBV_ILN_2107 GBV_ILN_2108 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2144 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2446 GBV_ILN_2470 GBV_ILN_2472 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4246 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4328 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4336 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 AR 4 2022 1 01 11 |
| allfields_unstemmed |
10.1007/s42979-022-01392-7 doi (DE-627)SPR048514853 (SPR)s42979-022-01392-7-e DE-627 ger DE-627 rakwb eng Solinas, Miguel verfasserin aut On the Beneficial Effects of Reinjections for Continual Learning 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. Incremental learning (dpeaa)DE-He213 Lifelong learning (dpeaa)DE-He213 Continual learning (dpeaa)DE-He213 Sequential learning (dpeaa)DE-He213 Pseudo-rehearsal (dpeaa)DE-He213 Rehearsal (dpeaa)DE-He213 Reyboz, Marina (orcid)0000-0002-3373-2908 aut Rousset, Stephane aut Galliere, Julie aut Mainsant, Marion aut Bourrier, Yannick aut Molnos, Anca aut Mermillod, Martial aut Enthalten in SN Computer Science Singapore : Springer Singapore, 2020 4(2022), 1 vom: 01. Nov. (DE-627)1668832976 (DE-600)2977367-2 2661-8907 nnns volume:4 year:2022 number:1 day:01 month:11 https://dx.doi.org/10.1007/s42979-022-01392-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_105 GBV_ILN_110 GBV_ILN_138 GBV_ILN_150 GBV_ILN_151 GBV_ILN_152 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_636 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2031 GBV_ILN_2034 GBV_ILN_2037 GBV_ILN_2038 GBV_ILN_2039 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2057 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2093 GBV_ILN_2106 GBV_ILN_2107 GBV_ILN_2108 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2144 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2446 GBV_ILN_2470 GBV_ILN_2472 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4246 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4328 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4336 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 AR 4 2022 1 01 11 |
| allfieldsGer |
10.1007/s42979-022-01392-7 doi (DE-627)SPR048514853 (SPR)s42979-022-01392-7-e DE-627 ger DE-627 rakwb eng Solinas, Miguel verfasserin aut On the Beneficial Effects of Reinjections for Continual Learning 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. Incremental learning (dpeaa)DE-He213 Lifelong learning (dpeaa)DE-He213 Continual learning (dpeaa)DE-He213 Sequential learning (dpeaa)DE-He213 Pseudo-rehearsal (dpeaa)DE-He213 Rehearsal (dpeaa)DE-He213 Reyboz, Marina (orcid)0000-0002-3373-2908 aut Rousset, Stephane aut Galliere, Julie aut Mainsant, Marion aut Bourrier, Yannick aut Molnos, Anca aut Mermillod, Martial aut Enthalten in SN Computer Science Singapore : Springer Singapore, 2020 4(2022), 1 vom: 01. Nov. (DE-627)1668832976 (DE-600)2977367-2 2661-8907 nnns volume:4 year:2022 number:1 day:01 month:11 https://dx.doi.org/10.1007/s42979-022-01392-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_105 GBV_ILN_110 GBV_ILN_138 GBV_ILN_150 GBV_ILN_151 GBV_ILN_152 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_636 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2031 GBV_ILN_2034 GBV_ILN_2037 GBV_ILN_2038 GBV_ILN_2039 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2057 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2093 GBV_ILN_2106 GBV_ILN_2107 GBV_ILN_2108 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2144 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2446 GBV_ILN_2470 GBV_ILN_2472 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4246 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4328 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4336 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 AR 4 2022 1 01 11 |
| allfieldsSound |
10.1007/s42979-022-01392-7 doi (DE-627)SPR048514853 (SPR)s42979-022-01392-7-e DE-627 ger DE-627 rakwb eng Solinas, Miguel verfasserin aut On the Beneficial Effects of Reinjections for Continual Learning 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. Incremental learning (dpeaa)DE-He213 Lifelong learning (dpeaa)DE-He213 Continual learning (dpeaa)DE-He213 Sequential learning (dpeaa)DE-He213 Pseudo-rehearsal (dpeaa)DE-He213 Rehearsal (dpeaa)DE-He213 Reyboz, Marina (orcid)0000-0002-3373-2908 aut Rousset, Stephane aut Galliere, Julie aut Mainsant, Marion aut Bourrier, Yannick aut Molnos, Anca aut Mermillod, Martial aut Enthalten in SN Computer Science Singapore : Springer Singapore, 2020 4(2022), 1 vom: 01. Nov. (DE-627)1668832976 (DE-600)2977367-2 2661-8907 nnns volume:4 year:2022 number:1 day:01 month:11 https://dx.doi.org/10.1007/s42979-022-01392-7 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_105 GBV_ILN_110 GBV_ILN_138 GBV_ILN_150 GBV_ILN_151 GBV_ILN_152 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_636 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2031 GBV_ILN_2034 GBV_ILN_2037 GBV_ILN_2038 GBV_ILN_2039 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2057 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2093 GBV_ILN_2106 GBV_ILN_2107 GBV_ILN_2108 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2144 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2446 GBV_ILN_2470 GBV_ILN_2472 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4246 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4328 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4336 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 AR 4 2022 1 01 11 |
| language |
English |
| source |
Enthalten in SN Computer Science 4(2022), 1 vom: 01. Nov. volume:4 year:2022 number:1 day:01 month:11 |
| sourceStr |
Enthalten in SN Computer Science 4(2022), 1 vom: 01. Nov. volume:4 year:2022 number:1 day:01 month:11 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Incremental learning Lifelong learning Continual learning Sequential learning Pseudo-rehearsal Rehearsal |
| isfreeaccess_bool |
false |
| container_title |
SN Computer Science |
| authorswithroles_txt_mv |
Solinas, Miguel @@aut@@ Reyboz, Marina @@aut@@ Rousset, Stephane @@aut@@ Galliere, Julie @@aut@@ Mainsant, Marion @@aut@@ Bourrier, Yannick @@aut@@ Molnos, Anca @@aut@@ Mermillod, Martial @@aut@@ |
| publishDateDaySort_date |
2022-11-01T00:00:00Z |
| hierarchy_top_id |
1668832976 |
| id |
SPR048514853 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR048514853</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230510060238.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221102s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s42979-022-01392-7</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR048514853</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s42979-022-01392-7-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Solinas, Miguel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">On the Beneficial Effects of Reinjections for Continual Learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Incremental learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Lifelong learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Continual learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Sequential learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pseudo-rehearsal</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Rehearsal</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Reyboz, Marina</subfield><subfield code="0">(orcid)0000-0002-3373-2908</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Rousset, Stephane</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Galliere, Julie</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mainsant, Marion</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bourrier, Yannick</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Molnos, Anca</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mermillod, Martial</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">SN Computer Science</subfield><subfield code="d">Singapore : Springer Singapore, 2020</subfield><subfield code="g">4(2022), 1 vom: 01. Nov.</subfield><subfield code="w">(DE-627)1668832976</subfield><subfield code="w">(DE-600)2977367-2</subfield><subfield code="x">2661-8907</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:4</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:1</subfield><subfield code="g">day:01</subfield><subfield code="g">month:11</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s42979-022-01392-7</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_138</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_250</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_281</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_636</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2006</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2031</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2039</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2057</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2093</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2107</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2108</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2144</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2446</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2472</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4246</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4328</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">4</subfield><subfield code="j">2022</subfield><subfield code="e">1</subfield><subfield code="b">01</subfield><subfield code="c">11</subfield></datafield></record></collection>
|
| author |
Solinas, Miguel |
| spellingShingle |
Solinas, Miguel misc Incremental learning misc Lifelong learning misc Continual learning misc Sequential learning misc Pseudo-rehearsal misc Rehearsal On the Beneficial Effects of Reinjections for Continual Learning |
| authorStr |
Solinas, Miguel |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)1668832976 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
2661-8907 |
| topic_title |
On the Beneficial Effects of Reinjections for Continual Learning Incremental learning (dpeaa)DE-He213 Lifelong learning (dpeaa)DE-He213 Continual learning (dpeaa)DE-He213 Sequential learning (dpeaa)DE-He213 Pseudo-rehearsal (dpeaa)DE-He213 Rehearsal (dpeaa)DE-He213 |
| topic |
misc Incremental learning misc Lifelong learning misc Continual learning misc Sequential learning misc Pseudo-rehearsal misc Rehearsal |
| topic_unstemmed |
misc Incremental learning misc Lifelong learning misc Continual learning misc Sequential learning misc Pseudo-rehearsal misc Rehearsal |
| topic_browse |
misc Incremental learning misc Lifelong learning misc Continual learning misc Sequential learning misc Pseudo-rehearsal misc Rehearsal |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
SN Computer Science |
| hierarchy_parent_id |
1668832976 |
| hierarchy_top_title |
SN Computer Science |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)1668832976 (DE-600)2977367-2 |
| title |
On the Beneficial Effects of Reinjections for Continual Learning |
| ctrlnum |
(DE-627)SPR048514853 (SPR)s42979-022-01392-7-e |
| title_full |
On the Beneficial Effects of Reinjections for Continual Learning |
| author_sort |
Solinas, Miguel |
| journal |
SN Computer Science |
| journalStr |
SN Computer Science |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| author_browse |
Solinas, Miguel Reyboz, Marina Rousset, Stephane Galliere, Julie Mainsant, Marion Bourrier, Yannick Molnos, Anca Mermillod, Martial |
| container_volume |
4 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Solinas, Miguel |
| doi_str_mv |
10.1007/s42979-022-01392-7 |
| normlink |
(ORCID)0000-0002-3373-2908 |
| normlink_prefix_str_mv |
(orcid)0000-0002-3373-2908 |
| title_sort |
on the beneficial effects of reinjections for continual learning |
| title_auth |
On the Beneficial Effects of Reinjections for Continual Learning |
| abstract |
Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstractGer |
Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstract_unstemmed |
Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_105 GBV_ILN_110 GBV_ILN_138 GBV_ILN_150 GBV_ILN_151 GBV_ILN_152 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_636 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2031 GBV_ILN_2034 GBV_ILN_2037 GBV_ILN_2038 GBV_ILN_2039 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2057 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2088 GBV_ILN_2093 GBV_ILN_2106 GBV_ILN_2107 GBV_ILN_2108 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2144 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2446 GBV_ILN_2470 GBV_ILN_2472 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4046 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4246 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4328 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4336 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 |
| container_issue |
1 |
| title_short |
On the Beneficial Effects of Reinjections for Continual Learning |
| url |
https://dx.doi.org/10.1007/s42979-022-01392-7 |
| remote_bool |
true |
| author2 |
Reyboz, Marina Rousset, Stephane Galliere, Julie Mainsant, Marion Bourrier, Yannick Molnos, Anca Mermillod, Martial |
| author2Str |
Reyboz, Marina Rousset, Stephane Galliere, Julie Mainsant, Marion Bourrier, Yannick Molnos, Anca Mermillod, Martial |
| ppnlink |
1668832976 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s42979-022-01392-7 |
| up_date |
2024-07-03T19:42:24.456Z |
| _version_ |
1803588200783937536 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR048514853</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230510060238.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221102s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s42979-022-01392-7</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR048514853</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s42979-022-01392-7-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Solinas, Miguel</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">On the Beneficial Effects of Reinjections for Continual Learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Deep learning delivers remarkable results in a wide range of applications, but artificial neural networks still suffer from catastrophic forgetting of old knowledge as new knowledge is learned. Rehearsal methods overcome catastrophic forgetting by replaying an amount of previously learned data stored in dedicated memory buffers. Alternatively, pseudo-rehearsal methods generate pseudo-samples to emulate previously learned data, alleviating the need for dedicated buffers. First, we show that it is possible to alleviate catastrophic forgetting with a pseudo-rehearsal method without employing memory buffers or generative models. We propose a hybrid architecture similar to that of an autoencoder with additional neurons to classify the input. This architecture preserves specific properties of autoencoders by allowing the generation of pseudo-samples through reinjections (i.e. iterative sampling) from random noise. The generated pseudo-samples are then interwoven with the new examples to acquire new knowledge without forgetting the previous ones. Second, we combine the two methods (rehearsal and pseudo-rehearsal) in the hybrid architecture. Examples stored in small memory buffers are employed as seeds instead of noise to improve the process of generating pseudo-samples and retrieving previously learned knowledge. We demonstrate that reinjections are suitable for rehearsal and pseudo-rehearsal approaches and show state-of-the-art results on rehearsal methods for small buffer sizes. We evaluate our method extensively on MNIST, CIFAR-10 and CIFAR-100 image classification datasets.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Incremental learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Lifelong learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Continual learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Sequential learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pseudo-rehearsal</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Rehearsal</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Reyboz, Marina</subfield><subfield code="0">(orcid)0000-0002-3373-2908</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Rousset, Stephane</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Galliere, Julie</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mainsant, Marion</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bourrier, Yannick</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Molnos, Anca</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mermillod, Martial</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">SN Computer Science</subfield><subfield code="d">Singapore : Springer Singapore, 2020</subfield><subfield code="g">4(2022), 1 vom: 01. Nov.</subfield><subfield code="w">(DE-627)1668832976</subfield><subfield code="w">(DE-600)2977367-2</subfield><subfield code="x">2661-8907</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:4</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:1</subfield><subfield code="g">day:01</subfield><subfield code="g">month:11</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s42979-022-01392-7</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_138</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_250</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_281</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_636</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2006</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2031</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2039</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2057</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2093</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2107</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2108</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2144</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2446</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2472</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4246</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4328</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">4</subfield><subfield code="j">2022</subfield><subfield code="e">1</subfield><subfield code="b">01</subfield><subfield code="c">11</subfield></datafield></record></collection>
|
| score |
7.4013834 |