Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance

Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performan...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Lloyd Pellatt [verfasserIn] Daniel Roggen [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning

Übergeordnetes Werk:	In: Frontiers in Computer Science - Frontiers Media S.A., 2019, 4(2022)
Übergeordnetes Werk:	volume:4 ; year:2022

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3389/fcomp.2022.914330

Katalog-ID:	DOAJ079744869

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ079744869
003	DE-627
005	20230307021118.0
007	cr uuu---uuuuu
008	230307s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3389/fcomp.2022.914330 \|2 doi
035			\|a (DE-627)DOAJ079744869
035			\|a (DE-599)DOAJf0581295114545a9a43cb26aadabab9c
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a QA75.5-76.95
100	0		\|a Lloyd Pellatt \|e verfasserin \|4 aut
245	1	0	\|a Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
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
520			\|a Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs.
650		4	\|a human activity recognition
650		4	\|a neural architecture search
650		4	\|a deep learning
650		4	\|a Wearable Computing
650		4	\|a wearable sensors
650		4	\|a reinforcement learning
653		0	\|a Electronic computers. Computer science
700	0		\|a Daniel Roggen \|e verfasserin \|4 aut
773	0	8	\|i In \|t Frontiers in Computer Science \|d Frontiers Media S.A., 2019 \|g 4(2022) \|w (DE-627)169122393X \|w (DE-600)3010036-7 \|x 26249898 \|7 nnns
773	1	8	\|g volume:4 \|g year:2022
856	4	0	\|u https://doi.org/10.3389/fcomp.2022.914330 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/f0581295114545a9a43cb26aadabab9c \|z kostenfrei
856	4	0	\|u https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2624-9898 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
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_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_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
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_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 4 \|j 2022

Indexfelder

author_variant	l p lp d r dr
matchkey_str	article:26249898:2022----::peigpeperlrhtcueerhowaalatvtrcgiinihalpe
hierarchy_sort_str	2022
callnumber-subject-code	QA
publishDate	2022
allfields	10.3389/fcomp.2022.914330 doi (DE-627)DOAJ079744869 (DE-599)DOAJf0581295114545a9a43cb26aadabab9c DE-627 ger DE-627 rakwb eng QA75.5-76.95 Lloyd Pellatt verfasserin aut Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs. human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning Electronic computers. Computer science Daniel Roggen verfasserin aut In Frontiers in Computer Science Frontiers Media S.A., 2019 4(2022) (DE-627)169122393X (DE-600)3010036-7 26249898 nnns volume:4 year:2022 https://doi.org/10.3389/fcomp.2022.914330 kostenfrei https://doaj.org/article/f0581295114545a9a43cb26aadabab9c kostenfrei https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full kostenfrei https://doaj.org/toc/2624-9898 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 4 2022
spelling	10.3389/fcomp.2022.914330 doi (DE-627)DOAJ079744869 (DE-599)DOAJf0581295114545a9a43cb26aadabab9c DE-627 ger DE-627 rakwb eng QA75.5-76.95 Lloyd Pellatt verfasserin aut Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs. human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning Electronic computers. Computer science Daniel Roggen verfasserin aut In Frontiers in Computer Science Frontiers Media S.A., 2019 4(2022) (DE-627)169122393X (DE-600)3010036-7 26249898 nnns volume:4 year:2022 https://doi.org/10.3389/fcomp.2022.914330 kostenfrei https://doaj.org/article/f0581295114545a9a43cb26aadabab9c kostenfrei https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full kostenfrei https://doaj.org/toc/2624-9898 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 4 2022
allfields_unstemmed	10.3389/fcomp.2022.914330 doi (DE-627)DOAJ079744869 (DE-599)DOAJf0581295114545a9a43cb26aadabab9c DE-627 ger DE-627 rakwb eng QA75.5-76.95 Lloyd Pellatt verfasserin aut Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs. human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning Electronic computers. Computer science Daniel Roggen verfasserin aut In Frontiers in Computer Science Frontiers Media S.A., 2019 4(2022) (DE-627)169122393X (DE-600)3010036-7 26249898 nnns volume:4 year:2022 https://doi.org/10.3389/fcomp.2022.914330 kostenfrei https://doaj.org/article/f0581295114545a9a43cb26aadabab9c kostenfrei https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full kostenfrei https://doaj.org/toc/2624-9898 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 4 2022
allfieldsGer	10.3389/fcomp.2022.914330 doi (DE-627)DOAJ079744869 (DE-599)DOAJf0581295114545a9a43cb26aadabab9c DE-627 ger DE-627 rakwb eng QA75.5-76.95 Lloyd Pellatt verfasserin aut Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs. human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning Electronic computers. Computer science Daniel Roggen verfasserin aut In Frontiers in Computer Science Frontiers Media S.A., 2019 4(2022) (DE-627)169122393X (DE-600)3010036-7 26249898 nnns volume:4 year:2022 https://doi.org/10.3389/fcomp.2022.914330 kostenfrei https://doaj.org/article/f0581295114545a9a43cb26aadabab9c kostenfrei https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full kostenfrei https://doaj.org/toc/2624-9898 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 4 2022
allfieldsSound	10.3389/fcomp.2022.914330 doi (DE-627)DOAJ079744869 (DE-599)DOAJf0581295114545a9a43cb26aadabab9c DE-627 ger DE-627 rakwb eng QA75.5-76.95 Lloyd Pellatt verfasserin aut Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs. human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning Electronic computers. Computer science Daniel Roggen verfasserin aut In Frontiers in Computer Science Frontiers Media S.A., 2019 4(2022) (DE-627)169122393X (DE-600)3010036-7 26249898 nnns volume:4 year:2022 https://doi.org/10.3389/fcomp.2022.914330 kostenfrei https://doaj.org/article/f0581295114545a9a43cb26aadabab9c kostenfrei https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full kostenfrei https://doaj.org/toc/2624-9898 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 4 2022
language	English
source	In Frontiers in Computer Science 4(2022) volume:4 year:2022
sourceStr	In Frontiers in Computer Science 4(2022) volume:4 year:2022
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning Electronic computers. Computer science
isfreeaccess_bool	true
container_title	Frontiers in Computer Science
authorswithroles_txt_mv	Lloyd Pellatt @@aut@@ Daniel Roggen @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	169122393X
id	DOAJ079744869
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ079744869</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230307021118.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230307s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fcomp.2022.914330</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ079744869</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJf0581295114545a9a43cb26aadabab9c</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="050" ind1=" " ind2="0"><subfield code="a">QA75.5-76.95</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Lloyd Pellatt</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance</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="520" ind1=" " ind2=" "><subfield code="a">Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">human activity recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">neural architecture search</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Wearable Computing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">wearable sensors</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">reinforcement learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic computers. Computer science</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daniel Roggen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Computer Science</subfield><subfield code="d">Frontiers Media S.A., 2019</subfield><subfield code="g">4(2022)</subfield><subfield code="w">(DE-627)169122393X</subfield><subfield code="w">(DE-600)3010036-7</subfield><subfield code="x">26249898</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></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fcomp.2022.914330</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/f0581295114545a9a43cb26aadabab9c</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2624-9898</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</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_DOAJ</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_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_95</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_151</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_213</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_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_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</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_4126</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_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_4335</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_4367</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></datafield></record></collection>
callnumber-first	Q - Science
author	Lloyd Pellatt
spellingShingle	Lloyd Pellatt misc QA75.5-76.95 misc human activity recognition misc neural architecture search misc deep learning misc Wearable Computing misc wearable sensors misc reinforcement learning misc Electronic computers. Computer science Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
authorStr	Lloyd Pellatt
ppnlink_with_tag_str_mv	@@773@@(DE-627)169122393X
format	electronic Article
delete_txt_mv	keep
author_role	aut aut
collection	DOAJ
remote_str	true
callnumber-label	QA75
illustrated	Not Illustrated
issn	26249898
topic_title	QA75.5-76.95 Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance human activity recognition neural architecture search deep learning Wearable Computing wearable sensors reinforcement learning
topic	misc QA75.5-76.95 misc human activity recognition misc neural architecture search misc deep learning misc Wearable Computing misc wearable sensors misc reinforcement learning misc Electronic computers. Computer science
topic_unstemmed	misc QA75.5-76.95 misc human activity recognition misc neural architecture search misc deep learning misc Wearable Computing misc wearable sensors misc reinforcement learning misc Electronic computers. Computer science
topic_browse	misc QA75.5-76.95 misc human activity recognition misc neural architecture search misc deep learning misc Wearable Computing misc wearable sensors misc reinforcement learning misc Electronic computers. Computer science
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Frontiers in Computer Science
hierarchy_parent_id	169122393X
hierarchy_top_title	Frontiers in Computer Science
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)169122393X (DE-600)3010036-7
title	Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
ctrlnum	(DE-627)DOAJ079744869 (DE-599)DOAJf0581295114545a9a43cb26aadabab9c
title_full	Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
author_sort	Lloyd Pellatt
journal	Frontiers in Computer Science
journalStr	Frontiers in Computer Science
callnumber-first-code	Q
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2022
contenttype_str_mv	txt
author_browse	Lloyd Pellatt Daniel Roggen
container_volume	4
class	QA75.5-76.95
format_se	Elektronische Aufsätze
author-letter	Lloyd Pellatt
doi_str_mv	10.3389/fcomp.2022.914330
author2-role	verfasserin
title_sort	speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
callnumber	QA75.5-76.95
title_auth	Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
abstract	Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs.
abstractGer	Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs.
abstract_unstemmed	Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
title_short	Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
url	https://doi.org/10.3389/fcomp.2022.914330 https://doaj.org/article/f0581295114545a9a43cb26aadabab9c https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full https://doaj.org/toc/2624-9898
remote_bool	true
author2	Daniel Roggen
author2Str	Daniel Roggen
ppnlink	169122393X
callnumber-subject	QA - Mathematics
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3389/fcomp.2022.914330
callnumber-a	QA75.5-76.95
up_date	2024-07-04T00:40:21.695Z
_version_	1803606946431893504
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ079744869</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230307021118.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230307s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fcomp.2022.914330</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ079744869</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJf0581295114545a9a43cb26aadabab9c</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="050" ind1=" " ind2="0"><subfield code="a">QA75.5-76.95</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Lloyd Pellatt</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance</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="520" ind1=" " ind2=" "><subfield code="a">Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neural regression methods for predicting the converged performance of a deep neural network (DNN) using validation performance in early epochs and topological and computational statistics. Our approach shows a significant improvement in predicting converged testing performance over a naive approach taking the ranking of the DNNs at an early epoch as an indication of their ranking on convergence. We apply this to the optimization of the convolutional feature extractor of an LSTM recurrent network using NAS with deep Q-learning, optimizing the kernel size, number of kernels, number of layers, and the connections between layers, allowing for arbitrary skip connections and dimensionality reduction with pooling layers. We find architectures which achieve up to 4% better F1 score on the recognition of gestures in the Opportunity dataset than our implementation of DeepConvLSTM and 0.8% better F1 score than our implementation of state-of-the-art model Attend and Discriminate, while reducing the search time by more than 90% over a random search. This opens the way to rapidly search for well-performing dataset-specific architectures. We describe the computational implementation of the system (software frameworks, computing resources) to enable replication of this work. Finally, we lay out several future research directions for NAS which the community may pursue to address ongoing challenges in human activity recognition, such as optimizing architectures to minimize power, minimize sensor usage, or minimize training data needs.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">human activity recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">neural architecture search</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Wearable Computing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">wearable sensors</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">reinforcement learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic computers. Computer science</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daniel Roggen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Computer Science</subfield><subfield code="d">Frontiers Media S.A., 2019</subfield><subfield code="g">4(2022)</subfield><subfield code="w">(DE-627)169122393X</subfield><subfield code="w">(DE-600)3010036-7</subfield><subfield code="x">26249898</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></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fcomp.2022.914330</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/f0581295114545a9a43cb26aadabab9c</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fcomp.2022.914330/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2624-9898</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</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_DOAJ</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_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_95</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_151</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_213</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_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_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</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_4126</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_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_4335</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_4367</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></datafield></record></collection>
score	7.3980722

Nicht das Richtige dabei?

Schreiben Sie uns!

Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?