Memory level neural network: A time-varying neural network for memory input processing
Affective computing is an important foundation for implementing brain-like computing and advanced machine intelligence. However, the instantaneous and memory fusion input characteristic makes current neural networks not suitable for affective computing. In this paper, we propose an affective computi...
Uloženo v:
| Vydáno v: | Neurocomputing (Amsterdam) Ročník 425; s. 256 - 265 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
15.02.2021
|
| Témata: | |
| ISSN: | 0925-2312, 1872-8286 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Affective computing is an important foundation for implementing brain-like computing and advanced machine intelligence. However, the instantaneous and memory fusion input characteristic makes current neural networks not suitable for affective computing. In this paper, we propose an affective computing oriented memory level neural network. A “switch” has been added to the memory level neurons, which will achieve a transition from the instantaneous input to the memory input when the temporal integration of inputs above a certain threshold. Then, the “switch” is continualized by an adjustable sigmoid function whose parameters are tuned to adjust the speed of the transition and the mixing ratio of the two inputs. Multiple memory level neurons form a deep time-varying neural network capable of handling fusional inputs. We demonstrate on both process datasets and static datasets that the memory level neural network successfully converges on both datasets and meets the error accuracy requirements. |
|---|---|
| AbstractList | Affective computing is an important foundation for implementing brain-like computing and advanced machine intelligence. However, the instantaneous and memory fusion input characteristic makes current neural networks not suitable for affective computing. In this paper, we propose an affective computing oriented memory level neural network. A “switch” has been added to the memory level neurons, which will achieve a transition from the instantaneous input to the memory input when the temporal integration of inputs above a certain threshold. Then, the “switch” is continualized by an adjustable sigmoid function whose parameters are tuned to adjust the speed of the transition and the mixing ratio of the two inputs. Multiple memory level neurons form a deep time-varying neural network capable of handling fusional inputs. We demonstrate on both process datasets and static datasets that the memory level neural network successfully converges on both datasets and meets the error accuracy requirements. |
| Author | Lin, Fuhong Lü, Xing Gong, Chao Zhou, Xianwei |
| Author_xml | – sequence: 1 givenname: Chao surname: Gong fullname: Gong, Chao organization: School of Computer and Communication Engineering, University of Science and Technology, Beijing Beijing 100083, China – sequence: 2 givenname: Xianwei surname: Zhou fullname: Zhou, Xianwei organization: School of Computer and Communication Engineering, University of Science and Technology, Beijing Beijing 100083, China – sequence: 3 givenname: Xing surname: Lü fullname: Lü, Xing organization: School of Computer and Communication Engineering, University of Science and Technology, Beijing Beijing 100083, China – sequence: 4 givenname: Fuhong surname: Lin fullname: Lin, Fuhong email: FHLin@ustb.edu.cn organization: School of Computer and Communication Engineering, University of Science and Technology, Beijing Beijing 100083, China |
| BookMark | eNqFkMtOwzAQRS1UJNrCH7DwDyR4nJfTBVJV8ZJAbICt5doT5JLEle0W9e9JFVZdwOouZs6V7pmRSe96JOQaWAoMyptN2uNOuy7ljLOU5SmrszMyBVHxRHBRTsiU1bxIeAb8gsxC2DAGFfB6Sj5esHP-QFvcY0uHGq-OEb-d_1rQJY22w2Sv_MH2nydn2jhPuxG3_XYX6dY7jSEMr5fkvFFtwKvfnJP3-7u31WPy_PrwtFo-JzpjZUwKU5UqY7UBYTSggdLAumyEKhosiiyrq7xELpo1B20arjiiyGtUAJgLhXk2J4uxV3sXgsdGahtVtK6PXtlWApNHQ3IjR0PyaEiyXA6GBjg_gbfedsPW_7DbEcNh2N6il0Fb7DUa61FHaZz9u-AHkp-G5w |
| CitedBy_id | crossref_primary_10_1002_oca_2840 crossref_primary_10_1109_ACCESS_2024_3450551 crossref_primary_10_1007_s00521_022_07760_x |
| Cites_doi | 10.3389/fnins.2019.00095 10.1016/j.neucom.2018.05.081 10.1155/2018/7068349 10.1109/TCYB.2017.2711961 10.1109/MCI.2018.2840738 10.23919/JCC.2019.08.011 10.1109/TSMC.2016.2606159 10.1109/JSSC.2016.2616357 10.1109/ACCESS.2018.2807385 10.1016/S0925-2312(01)00702-0 |
| ContentType | Journal Article |
| Copyright | 2020 Elsevier B.V. |
| Copyright_xml | – notice: 2020 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2020.04.093 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 265 |
| ExternalDocumentID | 10_1016_j_neucom_2020_04_093 S0925231220306780 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c306t-5d76a309d18dc1ed16d1b6f8a5fe55339746e28fb21cdf2a2ee849ea11e48ae43 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000632014300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0925-2312 |
| IngestDate | Sat Nov 29 07:11:55 EST 2025 Tue Nov 18 20:38:44 EST 2025 Fri Feb 23 02:48:54 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Affective computing Memory level transition MLNN Memory level neuron Time-varying output Time-related memory input |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-5d76a309d18dc1ed16d1b6f8a5fe55339746e28fb21cdf2a2ee849ea11e48ae43 |
| PageCount | 10 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_neucom_2020_04_093 crossref_primary_10_1016_j_neucom_2020_04_093 elsevier_sciencedirect_doi_10_1016_j_neucom_2020_04_093 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-02-15 |
| PublicationDateYYYYMMDD | 2021-02-15 |
| PublicationDate_xml | – month: 02 year: 2021 text: 2021-02-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861. Hecht-Nielsen (b0125) 1989 Jin, Song, Hu (b0065) 2019 Sak, Senior, Beaufays (b0110) 2014 Voulodimos, Doulamis, Doulamis, Protopapadakis (b0020) 2018 Young, Hazarika, Poria, Cambria (b0035) 2018; 13 Lee, Kim, Kang, Shin, Kim, Yoo (b0080) 2018 He, Xu (b0100) 2010 J. Villanueva-Valle, Facial expression of emotion, 2018. URL He, Huang, Ge (b0115) 2017; 47 H. Yao, F. Dai, S. Zhang, Y. Zhang, Q. Tian, C. Xu, Dr2-net: Deep residual reconstruction network for image compressive sensing, Neurocomputing. T. Bouwmans, S. Javed, M. Sultana, S.K. Jung, Deep neural network concepts for background subtraction: a systematic review and comparative evaluation, Neural Networks. Jiang, Kim, Wen, Wang (b0090) 2017; 2017 Wu, Dai, Zhang, Wang, Sun, Wu, Tian, Vajda, Jia, Keutzer (b0075) 2019 Mikolov, Karafiát, Burget, Černocký, Khudanpur (b0105) 2010 Zhang (b0095) 2003; 50 Shen, Zhou, Long, Jiang, Pan, Zhang (b0045) 2018 Hecht-Nielsen (b0010) 1992 Chen, Krishna, Emer, Sze (b0085) 2017; 52 A. Sengupta, Y. Ye, R. Wang, C. Liu, K. Roy, Going deeper in spiking neural networks: Vgg and residual architectures, Front. Neurosci. 13. D. Dheeru, E. Karra Taniskidou, UCI machine learning repository, 2017. URL Liu, Lu, Tong (b0120) 2017; 47 . Krizhevsky, Sutskever, Hinton (b0030) 2012 Akhtar, Mian (b0015) 2018; 6 M. Hebert, J.-P. Robichaud, C.M. Parisien, N. Duta, J. Tremblay, A. Almahairi, L. Kaushik, M. Boisvert, Multi-domain natural language processing architecture, uS Patent App. 10/282,419, May 7 2019. Gong, Lin, Zhou, Lü (b0005) 2019; 16 Morchid (b0050) 2018; 314 Jiang (10.1016/j.neucom.2020.04.093_b0090) 2017; 2017 10.1016/j.neucom.2020.04.093_b0070 Zhang (10.1016/j.neucom.2020.04.093_b0095) 2003; 50 He (10.1016/j.neucom.2020.04.093_b0115) 2017; 47 10.1016/j.neucom.2020.04.093_b0135 Hecht-Nielsen (10.1016/j.neucom.2020.04.093_b0010) 1992 10.1016/j.neucom.2020.04.093_b0055 Wu (10.1016/j.neucom.2020.04.093_b0075) 2019 Krizhevsky (10.1016/j.neucom.2020.04.093_b0030) 2012 10.1016/j.neucom.2020.04.093_b0130 Shen (10.1016/j.neucom.2020.04.093_b0045) 2018 Sak (10.1016/j.neucom.2020.04.093_b0110) 2014 Chen (10.1016/j.neucom.2020.04.093_b0085) 2017; 52 Mikolov (10.1016/j.neucom.2020.04.093_b0105) 2010 10.1016/j.neucom.2020.04.093_b0040 10.1016/j.neucom.2020.04.093_b0060 Lee (10.1016/j.neucom.2020.04.093_b0080) 2018 Jin (10.1016/j.neucom.2020.04.093_b0065) 2019 10.1016/j.neucom.2020.04.093_b0025 Young (10.1016/j.neucom.2020.04.093_b0035) 2018; 13 Akhtar (10.1016/j.neucom.2020.04.093_b0015) 2018; 6 Morchid (10.1016/j.neucom.2020.04.093_b0050) 2018; 314 He (10.1016/j.neucom.2020.04.093_b0100) 2010 Gong (10.1016/j.neucom.2020.04.093_b0005) 2019; 16 Hecht-Nielsen (10.1016/j.neucom.2020.04.093_b0125) 1989 Voulodimos (10.1016/j.neucom.2020.04.093_b0020) 2018 Liu (10.1016/j.neucom.2020.04.093_b0120) 2017; 47 |
| References_xml | – volume: 16 start-page: 115 year: 2019 end-page: 129 ident: b0005 article-title: Amygdala-inspired affective computing: to realize personalized intracranial emotions with accurately observed external emotions publication-title: China Commun. – reference: J. Villanueva-Valle, Facial expression of emotion, 2018. URL: – start-page: 1946 year: 2019 end-page: 1956 ident: b0065 article-title: Auto-keras: an efficient neural architecture search system publication-title: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining – year: 2018 ident: b0020 article-title: Deep learning for computer vision: a brief review publication-title: Comput. Intell. Neurosci. – start-page: 10734 year: 2019 end-page: 10742 ident: b0075 article-title: Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 1989 ident: b0125 article-title: Theory of the backpropagation neural network – volume: 47 start-page: 3136 year: 2017 end-page: 3147 ident: b0115 article-title: Adaptive neural network control of a robotic manipulator with time-varying output constraints publication-title: IEEE Trans. Cybern. – volume: 314 start-page: 48 year: 2018 end-page: 64 ident: b0050 article-title: Parsimonious memory unit for recurrent neural networks with application to natural language processing publication-title: Neurocomputing – reference: T. Bouwmans, S. Javed, M. Sultana, S.K. Jung, Deep neural network concepts for background subtraction: a systematic review and comparative evaluation, Neural Networks. – volume: 52 start-page: 127 year: 2017 end-page: 138 ident: b0085 article-title: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks publication-title: IEEE J. Solid-State Circuits – reference: A. Sengupta, Y. Ye, R. Wang, C. Liu, K. Roy, Going deeper in spiking neural networks: Vgg and residual architectures, Front. Neurosci. 13. – reference: D. Dheeru, E. Karra Taniskidou, UCI machine learning repository, 2017. URL: – year: 2010 ident: b0105 article-title: Recurrent neural network based language model publication-title: Eleventh Annual Conference of the International Speech Communication Association – start-page: 65 year: 1992 end-page: 93 ident: b0010 article-title: Theory of the backpropagation neural network publication-title: Neural networks for perception – year: 2014 ident: b0110 article-title: Long short-term memory recurrent neural network architectures for large scale acoustic modeling publication-title: Fifteenth Annual Conference of the International Speech Communication Association – volume: 6 start-page: 14410 year: 2018 end-page: 14430 ident: b0015 article-title: Threat of adversarial attacks on deep learning in computer vision: a survey publication-title: IEEE Access – start-page: 1097 year: 2012 end-page: 1105 ident: b0030 article-title: Imagenet classification with deep convolutional neural networks publication-title: International Conference on Neural Information Processing Systems – volume: 13 start-page: 55 year: 2018 end-page: 75 ident: b0035 article-title: Recent trends in deep learning based natural language processing publication-title: IEEE Computat. Intell. Mag. – year: 2018 ident: b0045 article-title: Disan: directional self-attention network for rnn/cnn-free language understanding publication-title: Thirty-Second AAAI Conference on Artificial Intelligence – volume: 47 start-page: 2060 year: 2017 end-page: 2068 ident: b0120 article-title: Neural network controller design for an uncertain robot with time-varying output constraint publication-title: IEEE Trans. Syst., Man, Cybern.: Syst. – reference: . – year: 2010 ident: b0100 article-title: Process Neural Networks: Theory and Applications – reference: H. Yao, F. Dai, S. Zhang, Y. Zhang, Q. Tian, C. Xu, Dr2-net: Deep residual reconstruction network for image compressive sensing, Neurocomputing. – start-page: 218 year: 2018 end-page: 220 ident: b0080 article-title: Unpu: a 50.6 tops/w unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision publication-title: 2018 IEEE International Solid-State Circuits Conference-(ISSCC) – reference: A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861. – volume: 2017 start-page: 1 year: 2017 end-page: 6 ident: b0090 article-title: Xnor-pop: a processing-in-memory architecture for binary convolutional neural networks in wide-io2 drams, in publication-title: IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED) – volume: 50 start-page: 159 year: 2003 end-page: 175 ident: b0095 article-title: Time series forecasting using a hybrid arima and neural network model publication-title: Neurocomputing – reference: M. Hebert, J.-P. Robichaud, C.M. Parisien, N. Duta, J. Tremblay, A. Almahairi, L. Kaushik, M. Boisvert, Multi-domain natural language processing architecture, uS Patent App. 10/282,419, May 7 2019. – start-page: 10734 year: 2019 ident: 10.1016/j.neucom.2020.04.093_b0075 article-title: Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search – ident: 10.1016/j.neucom.2020.04.093_b0055 – ident: 10.1016/j.neucom.2020.04.093_b0060 doi: 10.3389/fnins.2019.00095 – volume: 314 start-page: 48 year: 2018 ident: 10.1016/j.neucom.2020.04.093_b0050 article-title: Parsimonious memory unit for recurrent neural networks with application to natural language processing publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.081 – year: 1989 ident: 10.1016/j.neucom.2020.04.093_b0125 – year: 2018 ident: 10.1016/j.neucom.2020.04.093_b0020 article-title: Deep learning for computer vision: a brief review publication-title: Comput. Intell. Neurosci. doi: 10.1155/2018/7068349 – volume: 47 start-page: 3136 issue: 10 year: 2017 ident: 10.1016/j.neucom.2020.04.093_b0115 article-title: Adaptive neural network control of a robotic manipulator with time-varying output constraints publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2017.2711961 – year: 2010 ident: 10.1016/j.neucom.2020.04.093_b0100 – start-page: 65 year: 1992 ident: 10.1016/j.neucom.2020.04.093_b0010 article-title: Theory of the backpropagation neural network – year: 2010 ident: 10.1016/j.neucom.2020.04.093_b0105 article-title: Recurrent neural network based language model – year: 2014 ident: 10.1016/j.neucom.2020.04.093_b0110 article-title: Long short-term memory recurrent neural network architectures for large scale acoustic modeling – ident: 10.1016/j.neucom.2020.04.093_b0040 – ident: 10.1016/j.neucom.2020.04.093_b0025 – volume: 13 start-page: 55 issue: 3 year: 2018 ident: 10.1016/j.neucom.2020.04.093_b0035 article-title: Recent trends in deep learning based natural language processing publication-title: IEEE Computat. Intell. Mag. doi: 10.1109/MCI.2018.2840738 – ident: 10.1016/j.neucom.2020.04.093_b0130 – start-page: 1097 year: 2012 ident: 10.1016/j.neucom.2020.04.093_b0030 article-title: Imagenet classification with deep convolutional neural networks – volume: 16 start-page: 115 issue: 8 year: 2019 ident: 10.1016/j.neucom.2020.04.093_b0005 article-title: Amygdala-inspired affective computing: to realize personalized intracranial emotions with accurately observed external emotions publication-title: China Commun. doi: 10.23919/JCC.2019.08.011 – volume: 2017 start-page: 1 year: 2017 ident: 10.1016/j.neucom.2020.04.093_b0090 article-title: Xnor-pop: a processing-in-memory architecture for binary convolutional neural networks in wide-io2 drams, in publication-title: IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED) – volume: 47 start-page: 2060 issue: 8 year: 2017 ident: 10.1016/j.neucom.2020.04.093_b0120 article-title: Neural network controller design for an uncertain robot with time-varying output constraint publication-title: IEEE Trans. Syst., Man, Cybern.: Syst. doi: 10.1109/TSMC.2016.2606159 – volume: 52 start-page: 127 issue: 1 year: 2017 ident: 10.1016/j.neucom.2020.04.093_b0085 article-title: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks publication-title: IEEE J. Solid-State Circuits doi: 10.1109/JSSC.2016.2616357 – start-page: 218 year: 2018 ident: 10.1016/j.neucom.2020.04.093_b0080 article-title: Unpu: a 50.6 tops/w unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision – start-page: 1946 year: 2019 ident: 10.1016/j.neucom.2020.04.093_b0065 article-title: Auto-keras: an efficient neural architecture search system – year: 2018 ident: 10.1016/j.neucom.2020.04.093_b0045 article-title: Disan: directional self-attention network for rnn/cnn-free language understanding – volume: 6 start-page: 14410 year: 2018 ident: 10.1016/j.neucom.2020.04.093_b0015 article-title: Threat of adversarial attacks on deep learning in computer vision: a survey publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2807385 – ident: 10.1016/j.neucom.2020.04.093_b0070 – ident: 10.1016/j.neucom.2020.04.093_b0135 – volume: 50 start-page: 159 year: 2003 ident: 10.1016/j.neucom.2020.04.093_b0095 article-title: Time series forecasting using a hybrid arima and neural network model publication-title: Neurocomputing doi: 10.1016/S0925-2312(01)00702-0 |
| SSID | ssj0017129 |
| Score | 2.325972 |
| Snippet | Affective computing is an important foundation for implementing brain-like computing and advanced machine intelligence. However, the instantaneous and memory... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 256 |
| SubjectTerms | Affective computing Memory level neuron Memory level transition MLNN Time-related memory input Time-varying output |
| Title | Memory level neural network: A time-varying neural network for memory input processing |
| URI | https://dx.doi.org/10.1016/j.neucom.2020.04.093 |
| Volume | 425 |
| WOSCitedRecordID | wos000632014300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELZKlwMX3miXl3zgtgqqHSd2uJVql4fECokF9RY5sa1t1U2r0pT9D_xpxhknDRTxkrgk0cROrJkv9ngyD0KeyYJrVgoRxYkWkVCiiDJXukjHxiVSOhe7oik2Ic_O1HSavR8MvraxMNuFrCp1dZWt_quogQbC9qGzfyHu7qFAgGsQOhxB7HD8I8G_876zvhzE1i6OfbpK7U-NszeGofty8tFWr5sAp-8bNE6Hl_iAWbWqN8crDCRoF7h5m-ypBnpTECKYGsaXPuOC8fDqTAuvgrvv5EIvdwbqZe1pU4DlFzvr_IH8D_uXE7wT3uXJmOHgtL5YBmIwUHDmfZoxRBOtZnuRM2h-5EkEuiXOxBYnXyV5E9ben50FT_rza5L2lmqOZSb2VgE0SMyfAwu9SxAMaoT5bOPdqtf5In7wQ_Ej4c32SY2ukQMuk0wNycH4zcn0bfdTSjKOqRvD0NtIzMZdcP9dP9d0etrL-W1yM2w76BjhcocMbHWX3GpLetAww98jnxA9tEEPRXDQAI4XdEz72PnhNgXsUMQObbBDd9i5Tz6enpxPXkeh9EZUAhM2UWJkquNRZpgyJbOGpYYVqVM6cTaBHQLsQlPLlSs4K43jmlurRGY1Y1YobUX8gAyrZWUPCYVmTI4KA5p4KUputOE-WLuQaepKxeIjErdsysuQl96XR1nkrQPiPEfm5p65-UjkwNwjEnW9VpiX5TftZSuBPOiWqDPmAJpf9nz4zz0fkRu77-ExGW7WtX1Crpfbzezz-mlA1zevv6FB |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Memory+level+neural+network%3A+A+time-varying+neural+network+for+memory+input+processing&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Gong%2C+Chao&rft.au=Zhou%2C+Xianwei&rft.au=L%C3%BC%2C+Xing&rft.au=Lin%2C+Fuhong&rft.date=2021-02-15&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=425&rft.spage=256&rft.epage=265&rft_id=info:doi/10.1016%2Fj.neucom.2020.04.093&rft.externalDocID=S0925231220306780 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |