{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T01:43:05Z","timestamp":1781142185114,"version":"3.54.1"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T00:00:00Z","timestamp":1592179200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T00:00:00Z","timestamp":1592179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-020-0187-0","type":"journal-article","created":{"date-parts":[[2020,6,16]],"date-time":"2020-06-16T17:02:53Z","timestamp":1592326973000},"page":"325-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":151,"title":["Deep learning incorporating biologically inspired neural dynamics and in-memory computing"],"prefix":"10.1038","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7282-3792","authenticated-orcid":false,"given":"Stanis\u0142aw","family":"Wo\u017aniak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angeliki","family":"Pantazi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-9441","authenticated-orcid":false,"given":"Thomas","family":"Bohnstingl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3826-5931","authenticated-orcid":false,"given":"Evangelos","family":"Eleftheriou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,6,15]]},"reference":[{"key":"187_CR1","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 1097\u20131105 (NeurIPS, 2012)."},{"key":"187_CR2","doi-asserted-by":"publisher","unstructured":"Szegedy, C. et al. Going deeper with convolutions. In 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 1\u20139 (IEEE, 2015); https:\/\/doi.org\/10.1109\/CVPR.2015. 7298594.","DOI":"10.1109\/CVPR.2015."},{"key":"187_CR3","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2016); https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"187_CR4","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: unified, real-time object detection. In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2016); https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"187_CR5","doi-asserted-by":"publisher","unstructured":"He, K. et al. in IEEE Int. Conf. on Computer Vision (ICCV) 2980\u20132988 (IEEE, 2017); https:\/\/doi.org\/10.1109\/ICCV.2017.322.","DOI":"10.1109\/ICCV.2017.322"},{"key":"187_CR6","unstructured":"Sutskever, I., Vinyals, O. & Le, Q. V. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems 3104\u20133112 (NeurIPS, 2014)."},{"key":"187_CR7","unstructured":"Amodei, D. et al. Deep Speech 2: end-to-end speech recognition in English and Mandarin. In Proc. 33rd Int. Conf. on on Machine Learning Vol. 48, 173\u2013182 (JMLR, 2016)."},{"key":"187_CR8","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015).","journal-title":"Nature"},{"key":"187_CR9","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"187_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput"},{"key":"187_CR11","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D. & Bengio, Y. On the properties of neural machine translation: encoder-decoder approaches. In Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8) (Association for Computational Linguistics, 2014).","DOI":"10.3115\/v1\/W14-4012"},{"key":"187_CR12","unstructured":"Dayan, P. & Abbott, L. F. Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems (MIT Press, 2005)."},{"key":"187_CR13","doi-asserted-by":"crossref","unstructured":"Eliasmith, C. How to Build a Brain: A Neural Architecture for Biological Cognition (Oxford Univ. Press, 2013).","DOI":"10.1093\/acprof:oso\/9780199794546.001.0001"},{"key":"187_CR14","doi-asserted-by":"crossref","unstructured":"Gerstner, W., Kistler, W. M., Naud, R. & Paninski, L. Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition (Cambridge Univ. Press, 2014).","DOI":"10.1017\/CBO9781107447615"},{"key":"187_CR15","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.1126\/science.1225266","volume":"338","author":"C Eliasmith","year":"2012","unstructured":"Eliasmith, C. et al. A large-scale model of the functioning brain. Science 338, 1202\u20131205 (2012).","journal-title":"Science"},{"key":"187_CR16","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.intell.2013.10.003","volume":"42","author":"D Rasmussen","year":"2014","unstructured":"Rasmussen, D. & Eliasmith, C. A spiking neural model applied to the study of human performance and cognitive decline on Raven\u2019s Advanced Progressive Matrices. Intelligence 42, 53\u201382 (2014).","journal-title":"Intelligence"},{"key":"187_CR17","doi-asserted-by":"publisher","first-page":"2519","DOI":"10.1162\/089976600300014827","volume":"12","author":"W Maass","year":"2000","unstructured":"Maass, W. On the computational power of Winner-Take-All. Neural Comput. 12, 2519\u20132535 (2000).","journal-title":"Neural Comput."},{"key":"187_CR18","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1162\/089976602760407955","volume":"14","author":"W Maass","year":"2002","unstructured":"Maass, W., Natschl\u00e4ger, T. & Markram, H. Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14, 2531\u20132560 (2002).","journal-title":"Neural Comput."},{"key":"187_CR19","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1126\/science.275.5297.213","volume":"275","author":"H Markram","year":"1997","unstructured":"Markram, H., L\u00fcbke, J., Frotscher, M. & Sakmann, B. Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs. Science 275, 213\u2013215 (1997).","journal-title":"Science"},{"key":"187_CR20","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1038\/78829","volume":"3","author":"S Song","year":"2000","unstructured":"Song, S., Miller, K. D. & Abbott, L. F. Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nat. Neurosci. 3, 919\u2013926 (2000).","journal-title":"Nat. Neurosci."},{"key":"187_CR21","doi-asserted-by":"publisher","unstructured":"Moraitis, T. et al. Fatiguing STDP: learning from spike-timing codes in the presence of rate codes. In 2017 Int. Joint Conf. on Neural Networks (IJCNN) (IEEE, 2017); https:\/\/doi.org\/10.1109\/IJCNN.2017.7966072","DOI":"10.1109\/IJCNN.2017.7966072"},{"key":"187_CR22","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1038\/nnano.2016.70","volume":"11","author":"T Tuma","year":"2016","unstructured":"Tuma, T., Pantazi, A., Le Gallo, M., Sebastian, A. & Eleftheriou, E. Stochastic phase-change neurons. Nat. Nanotechnol. 11, 693\u2013699 (2016).","journal-title":"Nat. Nanotechnol."},{"key":"187_CR23","doi-asserted-by":"crossref","unstructured":"Wo\u017aniak, S., Tuma, T., Pantazi, A. & Eleftheriou, E. Learning spatio-temporal patterns in the presence of input noise using phase-change memristors. In IEEE Int. Symp. on Circuits and Systems (ISCAS) 365\u2013368 (IEEE, 2016).","DOI":"10.1109\/ISCAS.2016.7527246"},{"key":"187_CR24","doi-asserted-by":"publisher","first-page":"355205","DOI":"10.1088\/0957-4484\/27\/35\/355205","volume":"27","author":"A Pantazi","year":"2016","unstructured":"Pantazi, A., Wo\u017aniak, S., Tuma, T. & Eleftheriou, E. All-memristive neuromorphic computing with level-tuned neurons. Nanotechnology 27, 355205 (2016).","journal-title":"Nanotechnology"},{"key":"187_CR25","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1109\/LED.2016.2591181","volume":"37","author":"T Tuma","year":"2016","unstructured":"Tuma, T., Le Gallo, M., Sebastian, A. & Eleftheriou, E. Detecting correlations using phase-change neurons and synapses. IEEE Electron Device Lett. 37, 1238\u20131241 (2016).","journal-title":"IEEE Electron Device Lett."},{"key":"187_CR26","doi-asserted-by":"publisher","first-page":"3697","DOI":"10.1523\/JNEUROSCI.23-09-03697.2003","volume":"23","author":"R G\u00fctig","year":"2003","unstructured":"G\u00fctig, R., Aharonov, R., Rotter, S. & Sompolinsky, H. Learning input correlations through nonlinear temporally asymmetric Hebbian plasticity. J. Neurosci. 23, 3697\u20133714 (2003).","journal-title":"J. Neurosci."},{"key":"187_CR27","doi-asserted-by":"crossref","unstructured":"Diehl, P. U. & Cook, M. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 9, (2015).","DOI":"10.3389\/fncom.2015.00099"},{"key":"187_CR28","doi-asserted-by":"crossref","unstructured":"Sidler, S., Pantazi, A., Wo\u017aniak, S., Leblebici, Y. & Eleftheriou, E. Unsupervised learning using phase-change synapses and complementary patterns. In ENNS Int. Conf. on Artificial Neural Networks (ICANN) 281\u2013288 (Springer, 2017).","DOI":"10.1007\/978-3-319-68600-4_33"},{"key":"187_CR29","doi-asserted-by":"crossref","unstructured":"Querlioz, D., Bichler, O. & Gamrat, C. Simulation of a memristor-based spiking neural network immune to device variations. In Int. Joint Conf. on Neural Networks (IJCNN) 1775\u20131781 (IEEE, 2011).","DOI":"10.1109\/IJCNN.2011.6033439"},{"key":"187_CR30","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.neunet.2012.02.022","volume":"32","author":"O Bichler","year":"2012","unstructured":"Bichler, O., Querlioz, D., Thorpe, S. J., Bourgoin, J.-P. & Gamrat, C. Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity. Neural Netw. 32, 339\u2013348 (2012).","journal-title":"Neural Netw."},{"key":"187_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1004566","volume":"11","author":"KS Burbank","year":"2015","unstructured":"Burbank, K. S. Mirrored STDP implements autoencoder learning in a network of spiking neurons. PLoS Comput. Biol. 11, 1\u201325 (2015).","journal-title":"PLoS Comput. Biol."},{"key":"187_CR32","doi-asserted-by":"publisher","unstructured":"Wo\u017aniak, S., Pantazi, A., Leblebici, Y. & Eleftheriou, E. Neuromorphic system with phase-change synapses for pattern learning and feature extraction. In Int. Joint Conf. on Neural Networks (IJCNN) (IEEE, 2017); https:\/\/doi.org\/10.1109\/IJCNN.2017.7966325","DOI":"10.1109\/IJCNN.2017.7966325"},{"key":"187_CR33","doi-asserted-by":"publisher","first-page":"1629","DOI":"10.1109\/5.58356","volume":"78","author":"C Mead","year":"1990","unstructured":"Mead, C. Neuromorphic electronic systems. Proc. IEEE 78, 1629\u20131636 (1990).","journal-title":"Proc. IEEE"},{"key":"187_CR34","doi-asserted-by":"publisher","unstructured":"Meier, K. A mixed-signal universal neuromorphic computing system. In 2015 Int. Electron Devices Meet. (IEDM) 4.6.1\u20134.6.4 (IEEE, 2015); https:\/\/doi.org\/10.1109\/IEDM.2015.7409627.","DOI":"10.1109\/IEDM.2015.7409627"},{"key":"187_CR35","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/JPROC.2014.2313565","volume":"102","author":"BV Benjamin","year":"2014","unstructured":"Benjamin, B. V. et al. Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc. IEEE 102, 699\u2013716 (2014).","journal-title":"Proc. IEEE"},{"key":"187_CR36","doi-asserted-by":"publisher","unstructured":"Cassidy, A. S. et al. Real-time scalable cortical computing at 46 giga-synaptic OPS\/Watt with ~100x speedup in time-to-solution and ~100,000x reduction in energy-to-solution. in Proc. Int. Conf. for High Performance Computing, Networking, Storage and Analysis 27\u201338 (IEEE, 2014). https:\/\/doi.org\/10.1109\/SC.2014.8.","DOI":"10.1109\/SC.2014.8"},{"key":"187_CR37","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","volume":"38","author":"M Davies","year":"2018","unstructured":"Davies, M. et al. Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 82\u201399 (2018).","journal-title":"IEEE Micro"},{"key":"187_CR38","doi-asserted-by":"publisher","first-page":"2179","DOI":"10.1021\/nl201040y","volume":"12","author":"D Kuzum","year":"2012","unstructured":"Kuzum, D., Jeyasingh, R. G. D., Lee, B. & Wong, H.-S. P. Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing. Nano Lett. 12, 2179\u20132186 (2012).","journal-title":"Nano Lett."},{"key":"187_CR39","first-page":"89","volume":"2","author":"GW Burr","year":"2017","unstructured":"Burr, G. W. et al. Neuromorphic computing using non-volatile memory. Adv. Phys. X 2, 89\u2013124 (2017).","journal-title":"Adv. Phys. X"},{"key":"187_CR40","doi-asserted-by":"publisher","first-page":"111101","DOI":"10.1063\/1.5042413","volume":"124","author":"A Sebastian","year":"2018","unstructured":"Sebastian, A. et al. Tutorial: brain-inspired computing using phase-change memory devices. J. Appl. Phys. 124, 111101 (2018).","journal-title":"J. Appl. Phys."},{"key":"187_CR41","doi-asserted-by":"publisher","unstructured":"Chen, W. et al. A 65nm 1Mb nonvolatile computing-in-memory ReRAM macro with sub-16ns multiply-and-accumulate for binary DNN AI edge processors. In IEEE Int. Solid-State Circuits Conf. (ISSCC) 494\u2013496 (IEEE, 2018); https:\/\/doi.org\/10.1109\/ISSCC.2018.8310400.","DOI":"10.1109\/ISSCC.2018.8310400"},{"key":"187_CR42","doi-asserted-by":"publisher","unstructured":"Mochida, R. et al. A 4M synapses integrated analog ReRAM based 66.5 TOPS\/W neural-network processor with cell current controlled writing and flexible network architecture. In IEEE Symp. on VLSI Technology 175\u2013176 (IEEE, 2018). https:\/\/doi.org\/10.1109\/VLSIT.2018.8510676.","DOI":"10.1109\/VLSIT.2018.8510676"},{"key":"187_CR43","doi-asserted-by":"publisher","unstructured":"Xue, C.-X. et al. A 1Mb multibit ReRAM computing-in-memory macro with 14.6\u2009ns parallel MAC computing time for CNN based AI edge processors. In IEEE Int. Solid-State Circuits Conf. (ISSCC) 388\u2013390 (IEEE, 2019); https:\/\/doi.org\/10.1109\/ISSCC.2019.8662395.","DOI":"10.1109\/ISSCC.2019.8662395"},{"key":"187_CR44","first-page":"178","volume":"7","author":"P O\u2019Connor","year":"2013","unstructured":"O\u2019Connor, P., Neil, D., Liu, S.-C., Delbruck, T. & Pfeiffer, M. Real-time classification and sensor fusion with a spiking deep belief network. Front. Neurosci. 7, 178 (2013).","journal-title":"Front. Neurosci."},{"key":"187_CR45","doi-asserted-by":"crossref","unstructured":"Diehl, P. U., Zarrella, G., Cassidy, A., Pedroni, B. U. & Neftci, E. Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware. In IEEE Int. Conf. on Rebooting Computing (ICRC) 1\u20138 (IEEE, 2016).","DOI":"10.1109\/ICRC.2016.7738691"},{"key":"187_CR46","unstructured":"Hunsberger, E. & Eliasmith, C. Spiking deep networks with LIF neurons. Preprint at https:\/\/arxiv.org\/abs\/1510.08829 (2015)."},{"key":"187_CR47","doi-asserted-by":"publisher","unstructured":"Shrestha, A. et al. A spike-based long short-term memory on a neurosynaptic processor. In IEEE\/ACM Int. Conf. on Computer-Aided Design (ICCAD) 631\u2013637 (IEEE, 2017); https:\/\/doi.org\/10.1109\/ICCAD.2017.8203836.","DOI":"10.1109\/ICCAD.2017.8203836"},{"key":"187_CR48","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/S0925-2312(01)00658-0","volume":"48","author":"SM Bohte","year":"2002","unstructured":"Bohte, S. M., Kok, J. N. & La Poutr\u00e9, H. Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48, 17\u201337 (2002).","journal-title":"Neurocomputing"},{"key":"187_CR49","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.neunet.2018.03.019","volume":"103","author":"SR Kulkarni","year":"2018","unstructured":"Kulkarni, S. R. & Rajendran, B. Spiking neural networks for handwritten digit recognition\u2014supervised learning and network optimization. Neural Netw. 103, 118\u2013127 (2018).","journal-title":"Neural Netw."},{"key":"187_CR50","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1162\/NECO_a_00934","volume":"29","author":"Y Bengio","year":"2017","unstructured":"Bengio, Y., Mesnard, T., Fischer, A., Zhang, S. & Wu, Y. STDP-compatible approximation of backpropagation in an energy-based model. Neural Comput. 29, 555\u2013577 (2017).","journal-title":"Neural Comput."},{"key":"187_CR51","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2018.11.014","volume":"330","author":"A Tavanaei","year":"2019","unstructured":"Tavanaei, A. & Maida, A. BP-STDP: approximating backpropagation using spike timing dependent plasticity. Neurocomputing 330, 39\u201347 (2019).","journal-title":"Neurocomputing"},{"key":"187_CR52","doi-asserted-by":"publisher","first-page":"11441","DOI":"10.1073\/pnas.1604850113","volume":"113","author":"SK Esser","year":"2016","unstructured":"Esser, S. K. et al. Convolutional networks for fast, energy-efficient neuromorphic computing. Proc. Natl Acad. Sci. USA 113, 11441\u201311446 (2016).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"187_CR53","first-page":"508","volume":"10","author":"JH Lee","year":"2016","unstructured":"Lee, J. H., Delbruck, T. & Pfeiffer, M. Training deep spiking neural networks using backpropagation. Front. Neurosci. 10, 508 (2016).","journal-title":"Front. Neurosci."},{"key":"187_CR54","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/0893-6080(88)90007-X","volume":"1","author":"PJ Werbos","year":"1988","unstructured":"Werbos, P. J. Generalization of backpropagation with application to a recurrent gas market model. Neural Netw. 1, 339\u2013356 (1988).","journal-title":"Neural Netw."},{"key":"187_CR55","first-page":"1433","volume":"31","author":"D Huh","year":"2018","unstructured":"Huh, D. & Sejnowski, T. J. Gradient descent for spiking neural networks. Adv. Neural Inform. Processing Syst. 31, 1433\u20131443 (2018).","journal-title":"Adv. Neural Inform. Processing Syst."},{"key":"187_CR56","unstructured":"Bellec, G., Salaj, D., Subramoney, A., Legenstein, R. & Maass, W. Long short-term memory and learning-to-learn in networks of spiking neurons. In Advances in Neural Information Processing Systems 787\u2013797 (NeurIPS, 2018)."},{"key":"187_CR57","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3389\/fnins.2018.00331","volume":"12","author":"Y Wu","year":"2018","unstructured":"Wu, Y., Deng, L., Li, G., Zhu, J. & Shi, L. Spatio-temporal backpropagation for training high-performance spiking neural networks. Front. Neurosci. 12, 331 (2018).","journal-title":"Front. Neurosci."},{"key":"187_CR58","doi-asserted-by":"publisher","first-page":"774","DOI":"10.3389\/fnins.2018.00774","volume":"12","author":"M Pfeiffer","year":"2018","unstructured":"Pfeiffer, M. & Pfeil, T. Deep learning with spiking neurons: opportunities and challenges. Front. Neurosci. 12, 774 (2018).","journal-title":"Front. Neurosci."},{"key":"187_CR59","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3389\/fnins.2016.00056","volume":"10","author":"S Ambrogio","year":"2016","unstructured":"Ambrogio, S. et al. Unsupervised learning by spike timing dependent plasticity in phase change memory (PCM) synapses. Front. Neurosci. 10, 56 (2016).","journal-title":"Front. Neurosci."},{"key":"187_CR60","unstructured":"Wo\u017aniak, S., Pantazi, A., Bohnstingl, T. & Eleftheriou, E. Deep learning incorporating biologically-inspired neural dynamics. Preprint at https:\/\/arxiv.org\/abs\/1812.07040 (2018)."},{"key":"187_CR61","unstructured":"Neftci, E. O., Mostafa, H. & Zenke, F. Surrogate gradient learning in spiking neural networks. Preprint at https:\/\/arxiv.org\/abs\/1901.09948 (2019)."},{"key":"187_CR62","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","volume":"36","author":"EO Neftci","year":"2019","unstructured":"Neftci, E. O., Mostafa, H. & Zenke, F. Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Process. Mag. 36, 51\u201363 (2019).","journal-title":"IEEE Signal Process. Mag."},{"key":"187_CR63","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1113\/jphysiol.1952.sp004764","volume":"117","author":"AL Hodgkin","year":"1952","unstructured":"Hodgkin, A. L. & Huxley, A. F. A quantitative description of membrane current and its application to conduction and excitation in nerve. J. Physiol. 117, 500 (1952).","journal-title":"J. Physiol."},{"key":"187_CR64","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998).","journal-title":"Proc. IEEE"},{"key":"187_CR65","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M. P., Marcinkiewicz, M. A. & Santorini, B. Building a large annotated corpus of English: The Penn Treebank. Comput. Linguist 19, 313\u2013330 (1993).","journal-title":"Comput. Linguist"},{"key":"187_CR66","unstructured":"Boulanger-Lewandowski, N., Bengio, Y. & Vincent, P. Modeling temporal dependencies in high-dimensional sequences: application to polyphonic music generation and transcription. In Proc. 29th Int. Conf. on Machine Learning 1881\u20131888 (Omnipress, 2012)."},{"key":"187_CR67","unstructured":"Bengio, Y., L\u00e9onard, N. & Courville, A. Estimating or propagating gradients through stochastic neurons for conditional computation. Preprint at https:\/\/arxiv.org\/abs\/1305.2982 (2013)."},{"key":"187_CR68","unstructured":"Chollet, F. Deep Learning with Python (Manning, 2017)."},{"key":"187_CR69","doi-asserted-by":"crossref","unstructured":"Simard, P. Y., Steinkraus, D. & Platt, J. C. Best practices for convolutional neural networks applied to visual document analysis. In Proc. Seventh Int. Conf. on Document Analysis and Recognition Vol. 1, 958\u2013963 (IEEE Comput. Soc., 2003).","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"187_CR70","doi-asserted-by":"crossref","unstructured":"Press, O. & Wolf, L. Using the output embedding to improve language models. in Proc. 15th Conf. Eur. Chap. Association for Computational Linguistics Vol. 2 Short Papers 157\u2013163 (Association for Computational Linguistics, 2017).","DOI":"10.18653\/v1\/E17-2025"},{"key":"187_CR71","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2017","unstructured":"Greff, K., Srivastava, R. K., Koutn\u00edk, J., Steunebrink, B. R. & Schmidhuber, J. LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28, 2222\u20132232 (2017).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"187_CR72","unstructured":"Chung, J., Gulcehre, C., Cho, K. & Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. In NIPS Workshop on Deep Learning (NeurIPS, 2014)."},{"key":"187_CR73","doi-asserted-by":"crossref","unstructured":"Papandreou, N. et al. Programming algorithms for multilevel phase-change memory. In IEEE Int. Symp. on Circuits and Systems (ISCAS) 329\u2013332 (IEEE, 2011).","DOI":"10.1109\/ISCAS.2011.5937569"},{"key":"187_CR74","doi-asserted-by":"publisher","unstructured":"Burr, G. W. et al. Experimental demonstration and tolerancing of a large-scale neural network (165,000 synapses), using phase-change memory as the synaptic weight element. In 2014 IEEE Int. Electron Devices Meet. (IEDM) 29.5.1\u201329.5.4 (IEEE, 2014); https:\/\/doi.org\/10.1109\/IEDM.2014.7047135.","DOI":"10.1109\/IEDM.2014.7047135"},{"key":"187_CR75","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"1999","unstructured":"Gers, F. A., Schmidhuber, J. & Cummins, F. Learning to forget: continual prediction with LSTM. Neural Comput. 12, 2451\u20132471 (1999).","journal-title":"Neural Comput."},{"key":"187_CR76","unstructured":"Nair, V. & Hinton, G. E. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on International Conference on Machine Learning 807\u2013814 (Omnipress, 2010)."},{"key":"187_CR77","unstructured":"Maas, A. L., Hannun, A. Y. & Ng, A. Y. Rectifier nonlinearities improve neural network acoustic models. In ICML Workshop on Deep Learning for Audio, Speech and Language Processing (JMLR, 2013)."},{"key":"187_CR78","unstructured":"TensorFlow. An end-to-end open source machine learning platform; http:\/\/www.tensorflow.org."},{"key":"187_CR79","unstructured":"Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Int. Conf. on Artificial Intelligence and Statistics 249\u2013256 (2010)."},{"key":"187_CR80","unstructured":"Mikolov, T. Penn Treebank dataset; http:\/\/www.fit.vutbr.cz\/~imikolov\/rnnlm\/simple-examples.tgz."},{"key":"187_CR81","unstructured":"Zaremba, W., Sutskever, I. & Vinyals, O. Recurrent neural network regularization. Preprint at https:\/\/arxiv.org\/abs\/1409.2329 (2014)."},{"key":"187_CR82","doi-asserted-by":"publisher","unstructured":"Close, G. F. et al. Device, circuit and system-level analysis of noise in multi-bit phase-change memory. In IEEE Int. Electron Devices Meeting (IEDM) 29.5.1\u201329.5.4 (IEEE, 2010); https:\/\/doi.org\/10.1109\/IEDM.2010.5703445.","DOI":"10.1109\/IEDM.2010.5703445"},{"key":"187_CR83","doi-asserted-by":"publisher","first-page":"152135","DOI":"10.1063\/1.5042408","volume":"124","author":"SR Nandakumar","year":"2018","unstructured":"Nandakumar, S. R. et al. A phase-change memory model for neuromorphic computing. J. Appl. Phys. 124, 152135 (2018).","journal-title":"J. Appl. Phys."},{"key":"187_CR84","doi-asserted-by":"publisher","unstructured":"Gallo, M. L., Sebastian, A., Cherubini, G., Giefers, H. & Eleftheriou, E. Compressed sensing with approximate message passing using in-memory computing. In IEEE Trans. Electron Devices 1\u20139 (2018); https:\/\/doi.org\/10.1109\/TED.2018.2865352.","DOI":"10.1109\/TED.2018.2865352"},{"key":"187_CR85","doi-asserted-by":"publisher","unstructured":"Nandakumar, S. R. et al. Mixed-precision architecture based on computational memory for training deep neural networks. In IEEE Int. Symp. on Circuits and Systems (ISCAS) 1\u20135 (IEEE, 2018); https:\/\/doi.org\/10.1109\/ISCAS.2018.8351656.","DOI":"10.1109\/ISCAS.2018.8351656"},{"key":"187_CR86","doi-asserted-by":"publisher","first-page":"e47314","DOI":"10.7554\/eLife.47314","volume":"8","author":"M Stimberg","year":"2019","unstructured":"Stimberg, M., Brette, R. & Goodman, D. F. M. Brian 2, an intuitive and efficient neural simulator. eLife 8, e47314 (2019).","journal-title":"eLife"},{"key":"187_CR87","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.neucom.2016.04.029","volume":"205","author":"SR Kheradpisheh","year":"2016","unstructured":"Kheradpisheh, S. R., Ganjtabesh, M. & Masquelier, T. Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition. Neurocomputing 205, 382\u2013392 (2016).","journal-title":"Neurocomputing"},{"key":"187_CR88","first-page":"425","volume":"12","author":"C Lee","year":"2018","unstructured":"Lee, C., Panda, P., Srinivasan, G. & Roy, K. Training deep spiking convolutional neural networks with STDP-based unsupervised pre-training followed by supervised fine-tuning. Front. Neurosci. 12, 425 (2018).","journal-title":"Front. Neurosci."},{"key":"187_CR89","doi-asserted-by":"publisher","unstructured":"Mikolov, T., Kombrink, S., Burget, L., Cernocky, J. & Khudanpur, S. Extensions of recurrent neural network language model. In IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP) 5528\u20135531 (IEEE, 2011); https:\/\/doi.org\/10.1109\/ICASSP.2011.5947611.","DOI":"10.1109\/ICASSP.2011.5947611"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-0187-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-0187-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-0187-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T19:31:23Z","timestamp":1723059083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-0187-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,15]]},"references-count":89,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["187"],"URL":"https:\/\/doi.org\/10.1038\/s42256-020-0187-0","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,15]]},"assertion":[{"value":"17 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}