RASP: Regularization-based Amplitude Saliency Pruning

Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude me...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Zhen, Chenghui [verfasserIn] Zhang, Weiwei [verfasserIn] Mo, Jian [verfasserIn] Ji, Ming [verfasserIn] Zhou, Hongbo [verfasserIn] Zhu, Jianqing [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	Model compression Filter pruning Pruning criterion Regularization

Übergeordnetes Werk:	Enthalten in: Neural networks - Amsterdam : Elsevier, 1988, 168, Seite 1-13
Übergeordnetes Werk:	volume:168 ; pages:1-13

DOI / URN:	10.1016/j.neunet.2023.09.002

Katalog-ID:	ELV065497236

Internformat


LEADER	01000caa a22002652 4500
001	ELV065497236
003	DE-627
005	20231125093228.0
007	cr uuu---uuuuu
008	231109s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1016/j.neunet.2023.09.002 \|2 doi
035			\|a (DE-627)ELV065497236
035			\|a (ELSEVIER)S0893-6080(23)00496-3
040			\|a DE-627 \|b ger \|c DE-627 \|e rda
041			\|a eng
082	0	4	\|a 004 \|q VZ
084			\|a 54.72 \|2 bkl
100	1		\|a Zhen, Chenghui \|e verfasserin \|4 aut
245	1	0	\|a RASP: Regularization-based Amplitude Saliency Pruning
264		1	\|c 2023
336			\|a nicht spezifiziert \|b zzz \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50.
650		4	\|a Model compression
650		4	\|a Filter pruning
650		4	\|a Pruning criterion
650		4	\|a Regularization
700	1		\|a Zhang, Weiwei \|e verfasserin \|0 (orcid)0000-0002-7285-8714 \|4 aut
700	1		\|a Mo, Jian \|e verfasserin \|4 aut
700	1		\|a Ji, Ming \|e verfasserin \|4 aut
700	1		\|a Zhou, Hongbo \|e verfasserin \|4 aut
700	1		\|a Zhu, Jianqing \|e verfasserin \|4 aut
773	0	8	\|i Enthalten in \|t Neural networks \|d Amsterdam : Elsevier, 1988 \|g 168, Seite 1-13 \|h Online-Ressource \|w (DE-627)302468536 \|w (DE-600)1491372-0 \|w (DE-576)07971997X \|x 1879-2782 \|7 nnns
773	1	8	\|g volume:168 \|g pages:1-13
912			\|a GBV_USEFLAG_U
912			\|a GBV_ELV
912			\|a SYSFLAG_U
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_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
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_101
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_150
912			\|a GBV_ILN_151
912			\|a GBV_ILN_187
912			\|a GBV_ILN_213
912			\|a GBV_ILN_224
912			\|a GBV_ILN_230
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
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_2007
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_2034
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_2059
912			\|a GBV_ILN_2061
912			\|a GBV_ILN_2064
912			\|a GBV_ILN_2106
912			\|a GBV_ILN_2110
912			\|a GBV_ILN_2111
912			\|a GBV_ILN_2112
912			\|a GBV_ILN_2122
912			\|a GBV_ILN_2129
912			\|a GBV_ILN_2143
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_2470
912			\|a GBV_ILN_2507
912			\|a GBV_ILN_4035
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4242
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_4326
912			\|a GBV_ILN_4333
912			\|a GBV_ILN_4334
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4393
912			\|a GBV_ILN_4700
936	b	k	\|a 54.72 \|j Künstliche Intelligenz \|q VZ
951			\|a AR
952			\|d 168 \|h 1-13

Indexfelder

author_variant	c z cz w z wz j m jm m j mj h z hz j z jz
matchkey_str	article:18792782:2023----::apeuaiainaeapiue
hierarchy_sort_str	2023
bklnumber	54.72
publishDate	2023
allfields	10.1016/j.neunet.2023.09.002 doi (DE-627)ELV065497236 (ELSEVIER)S0893-6080(23)00496-3 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Zhen, Chenghui verfasserin aut RASP: Regularization-based Amplitude Saliency Pruning 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50. Model compression Filter pruning Pruning criterion Regularization Zhang, Weiwei verfasserin (orcid)0000-0002-7285-8714 aut Mo, Jian verfasserin aut Ji, Ming verfasserin aut Zhou, Hongbo verfasserin aut Zhu, Jianqing verfasserin aut Enthalten in Neural networks Amsterdam : Elsevier, 1988 168, Seite 1-13 Online-Ressource (DE-627)302468536 (DE-600)1491372-0 (DE-576)07971997X 1879-2782 nnns volume:168 pages:1-13 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 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_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 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_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 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_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 168 1-13
spelling	10.1016/j.neunet.2023.09.002 doi (DE-627)ELV065497236 (ELSEVIER)S0893-6080(23)00496-3 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Zhen, Chenghui verfasserin aut RASP: Regularization-based Amplitude Saliency Pruning 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50. Model compression Filter pruning Pruning criterion Regularization Zhang, Weiwei verfasserin (orcid)0000-0002-7285-8714 aut Mo, Jian verfasserin aut Ji, Ming verfasserin aut Zhou, Hongbo verfasserin aut Zhu, Jianqing verfasserin aut Enthalten in Neural networks Amsterdam : Elsevier, 1988 168, Seite 1-13 Online-Ressource (DE-627)302468536 (DE-600)1491372-0 (DE-576)07971997X 1879-2782 nnns volume:168 pages:1-13 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 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_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 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_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 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_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 168 1-13
allfields_unstemmed	10.1016/j.neunet.2023.09.002 doi (DE-627)ELV065497236 (ELSEVIER)S0893-6080(23)00496-3 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Zhen, Chenghui verfasserin aut RASP: Regularization-based Amplitude Saliency Pruning 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50. Model compression Filter pruning Pruning criterion Regularization Zhang, Weiwei verfasserin (orcid)0000-0002-7285-8714 aut Mo, Jian verfasserin aut Ji, Ming verfasserin aut Zhou, Hongbo verfasserin aut Zhu, Jianqing verfasserin aut Enthalten in Neural networks Amsterdam : Elsevier, 1988 168, Seite 1-13 Online-Ressource (DE-627)302468536 (DE-600)1491372-0 (DE-576)07971997X 1879-2782 nnns volume:168 pages:1-13 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 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_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 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_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 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_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 168 1-13
allfieldsGer	10.1016/j.neunet.2023.09.002 doi (DE-627)ELV065497236 (ELSEVIER)S0893-6080(23)00496-3 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Zhen, Chenghui verfasserin aut RASP: Regularization-based Amplitude Saliency Pruning 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50. Model compression Filter pruning Pruning criterion Regularization Zhang, Weiwei verfasserin (orcid)0000-0002-7285-8714 aut Mo, Jian verfasserin aut Ji, Ming verfasserin aut Zhou, Hongbo verfasserin aut Zhu, Jianqing verfasserin aut Enthalten in Neural networks Amsterdam : Elsevier, 1988 168, Seite 1-13 Online-Ressource (DE-627)302468536 (DE-600)1491372-0 (DE-576)07971997X 1879-2782 nnns volume:168 pages:1-13 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 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_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 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_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 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_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 168 1-13
allfieldsSound	10.1016/j.neunet.2023.09.002 doi (DE-627)ELV065497236 (ELSEVIER)S0893-6080(23)00496-3 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Zhen, Chenghui verfasserin aut RASP: Regularization-based Amplitude Saliency Pruning 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50. Model compression Filter pruning Pruning criterion Regularization Zhang, Weiwei verfasserin (orcid)0000-0002-7285-8714 aut Mo, Jian verfasserin aut Ji, Ming verfasserin aut Zhou, Hongbo verfasserin aut Zhu, Jianqing verfasserin aut Enthalten in Neural networks Amsterdam : Elsevier, 1988 168, Seite 1-13 Online-Ressource (DE-627)302468536 (DE-600)1491372-0 (DE-576)07971997X 1879-2782 nnns volume:168 pages:1-13 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 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_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 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_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 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_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 168 1-13
language	English
source	Enthalten in Neural networks 168, Seite 1-13 volume:168 pages:1-13
sourceStr	Enthalten in Neural networks 168, Seite 1-13 volume:168 pages:1-13
format_phy_str_mv	Article
bklname	Künstliche Intelligenz
institution	findex.gbv.de
topic_facet	Model compression Filter pruning Pruning criterion Regularization
dewey-raw	004
isfreeaccess_bool	false
container_title	Neural networks
authorswithroles_txt_mv	Zhen, Chenghui @@aut@@ Zhang, Weiwei @@aut@@ Mo, Jian @@aut@@ Ji, Ming @@aut@@ Zhou, Hongbo @@aut@@ Zhu, Jianqing @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	302468536
dewey-sort	14
id	ELV065497236
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">ELV065497236</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20231125093228.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">231109s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.neunet.2023.09.002</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV065497236</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0893-6080(23)00496-3</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">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhen, Chenghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">RASP: Regularization-based Amplitude Saliency Pruning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</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="520" ind1=" " ind2=" "><subfield code="a">Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Model compression</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Filter pruning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pruning criterion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Regularization</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Weiwei</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-7285-8714</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mo, Jian</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ji, Ming</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhou, Hongbo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhu, Jianqing</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural networks</subfield><subfield code="d">Amsterdam : Elsevier, 1988</subfield><subfield code="g">168, Seite 1-13</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)302468536</subfield><subfield code="w">(DE-600)1491372-0</subfield><subfield code="w">(DE-576)07971997X</subfield><subfield code="x">1879-2782</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:168</subfield><subfield code="g">pages:1-13</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</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_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_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_101</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_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_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_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_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_2007</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_2034</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_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_2106</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_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_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_2470</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_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_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_4242</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_4326</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_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="936" ind1="b" ind2="k"><subfield code="a">54.72</subfield><subfield code="j">Künstliche Intelligenz</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">168</subfield><subfield code="h">1-13</subfield></datafield></record></collection>
author	Zhen, Chenghui
spellingShingle	Zhen, Chenghui ddc 004 bkl 54.72 misc Model compression misc Filter pruning misc Pruning criterion misc Regularization RASP: Regularization-based Amplitude Saliency Pruning
authorStr	Zhen, Chenghui
ppnlink_with_tag_str_mv	@@773@@(DE-627)302468536
format	electronic Article
dewey-ones	004 - Data processing & computer science
delete_txt_mv	keep
author_role	aut aut aut aut aut aut
collection	elsevier
remote_str	true
illustrated	Not Illustrated
issn	1879-2782
topic_title	004 VZ 54.72 bkl RASP: Regularization-based Amplitude Saliency Pruning Model compression Filter pruning Pruning criterion Regularization
topic	ddc 004 bkl 54.72 misc Model compression misc Filter pruning misc Pruning criterion misc Regularization
topic_unstemmed	ddc 004 bkl 54.72 misc Model compression misc Filter pruning misc Pruning criterion misc Regularization
topic_browse	ddc 004 bkl 54.72 misc Model compression misc Filter pruning misc Pruning criterion misc Regularization
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Neural networks
hierarchy_parent_id	302468536
dewey-tens	000 - Computer science, knowledge & systems
hierarchy_top_title	Neural networks
isfreeaccess_txt	false
familylinks_str_mv	(DE-627)302468536 (DE-600)1491372-0 (DE-576)07971997X
title	RASP: Regularization-based Amplitude Saliency Pruning
ctrlnum	(DE-627)ELV065497236 (ELSEVIER)S0893-6080(23)00496-3
title_full	RASP: Regularization-based Amplitude Saliency Pruning
author_sort	Zhen, Chenghui
journal	Neural networks
journalStr	Neural networks
lang_code	eng
isOA_bool	false
dewey-hundreds	000 - Computer science, information & general works
recordtype	marc
publishDateSort	2023
contenttype_str_mv	zzz
container_start_page	1
author_browse	Zhen, Chenghui Zhang, Weiwei Mo, Jian Ji, Ming Zhou, Hongbo Zhu, Jianqing
container_volume	168
class	004 VZ 54.72 bkl
format_se	Elektronische Aufsätze
author-letter	Zhen, Chenghui
doi_str_mv	10.1016/j.neunet.2023.09.002
normlink	(ORCID)0000-0002-7285-8714
normlink_prefix_str_mv	(orcid)0000-0002-7285-8714
dewey-full	004
author2-role	verfasserin
title_sort	rasp: regularization-based amplitude saliency pruning
title_auth	RASP: Regularization-based Amplitude Saliency Pruning
abstract	Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50.
abstractGer	Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50.
abstract_unstemmed	Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50.
collection_details	GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 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_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 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_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 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_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700
title_short	RASP: Regularization-based Amplitude Saliency Pruning
remote_bool	true
author2	Zhang, Weiwei Mo, Jian Ji, Ming Zhou, Hongbo Zhu, Jianqing
author2Str	Zhang, Weiwei Mo, Jian Ji, Ming Zhou, Hongbo Zhu, Jianqing
ppnlink	302468536
mediatype_str_mv	c
isOA_txt	false
hochschulschrift_bool	false
doi_str	10.1016/j.neunet.2023.09.002
up_date	2024-07-06T23:14:11.829Z
_version_	1803873316326342656
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">ELV065497236</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20231125093228.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">231109s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.neunet.2023.09.002</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV065497236</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0893-6080(23)00496-3</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">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhen, Chenghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">RASP: Regularization-based Amplitude Saliency Pruning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</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="520" ind1=" " ind2=" "><subfield code="a">Due to the prevalent data-dependent nature of existing pruning criteria, norm criteria with data independence play a crucial role in filter pruning criteria, providing promising prospects for deploying deep neural networks on resource-constrained devices. However, norm criteria based on amplitude measurements have long posed challenges in terms of theoretical feasibility. Existing methods rely on data-derived information such as derivatives to establish reasonable pruning standards. Nonetheless, achieving quantitative analysis of the “smaller-norm-less-important” notion remains elusive within the norm criterion context. To address the need for data independence and theoretical feasibility, we conducted saliency analysis on filters and proposed a regularization-based amplitude saliency pruning criterion (RASP). This amplitude saliency not only attains data independence but also establishes norm criteria for usage guidelines. Furthermore, we further investigated the amplitude saliency, addressing the issues of data dependency in model evaluation and inter-class filter selection. We introduced model saliency and an adaptive parameter group lasso (AGL) regularization approach sensitive to different layers. Theoretically, we thoroughly analyzed the feasibility of amplitude saliency and employed quantitative saliency analysis to validate the advantages of our method over previous approaches. Experimentally, conducted on the CIFAR-10 and ImageNet image classification benchmarks, we extensively validated the improved top-level performance of our method compared to previous methods. Even when the pruned model has the same or even smaller number of FLOP, our method can achieve equivalent or higher model accuracy. Notably, in our ImageNet experiment, RASP achieved a 51.9% reduction in FLOPs while maintaining an accuracy of 76.19% on ResNet-50.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Model compression</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Filter pruning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pruning criterion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Regularization</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Weiwei</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-7285-8714</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Mo, Jian</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ji, Ming</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhou, Hongbo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhu, Jianqing</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural networks</subfield><subfield code="d">Amsterdam : Elsevier, 1988</subfield><subfield code="g">168, Seite 1-13</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)302468536</subfield><subfield code="w">(DE-600)1491372-0</subfield><subfield code="w">(DE-576)07971997X</subfield><subfield code="x">1879-2782</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:168</subfield><subfield code="g">pages:1-13</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</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_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_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_101</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_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_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_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_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_2007</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_2034</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_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_2106</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_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_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_2470</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_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_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_4242</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_4326</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_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="936" ind1="b" ind2="k"><subfield code="a">54.72</subfield><subfield code="j">Künstliche Intelligenz</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">168</subfield><subfield code="h">1-13</subfield></datafield></record></collection>
score	7.4011583

Nicht das Richtige dabei?

Schreiben Sie uns!

RASP: Regularization-based Amplitude Saliency Pruning

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?