Влияние корреляции спайковых последовательностей на обучение нейронной сети под действием Spike-Timing-Dependent Plasticity
https://doi.org/10.1134/S2304487X20010083
Аннотация
Об авторах
А. Г. Сбоев
Национальный исследовательский ядерный университет “МИФИ”; Национальный исследовательский центр “Курчатовский институт”
Россия
Россия
115409
123182
Москва
Р. Б. Рыбка
Национальный исследовательский центр “Курчатовский институт”
Россия
Россия
123182
Москва
А. В. Серенко
Национальный исследовательский центр “Курчатовский институт”
Россия
Россия
123182
Москва
Список литературы
1. Srinjoy Mitra, Stefano Fusi, and Giacomo Indiveri. Realtime classification of complex patterns using spike-based learning in neuromorphic VLSI. Biomedical Circuits and Systems, IEEE Transactions on. 2009. V. 3 (1). P. 32–42.
2. Paul A. Merolla, John V. Arthur, Rodrigo Alvarez-Icaza, Andrew S. Cassidy, Jun Sawada, Filipp Akopyan, Bryan L. Jackson, Nabil Imam, Chen Guo, Yutaka Nakamura, et al. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science. 2014. V. 345 (6197). P. 668–673.
3. Thomas Pfeil, Tobias C. Potjans, Sven Schrader, Wiebke Potjans, Johannes Schemmel, Markus Diesmann, and Karlheinz Meier. Is a 4-bit synaptic weight resolution enough? – constraints on enabling spike-timing dependent plasticity in neuromorphic hardware. Frontiers in neuroscience. 2012. V. 6. P. 90.
4. Steven K. Esser, Paul A. Merolla, John V. Arthur, Andrew S. Cassidy, Rathinakumar Appuswamy, Alexander Andreopoulos, David J. Berg, Jeffrey L. McKinstry, Timothy Melano, Davis R. Barch, et al. Convolutional networks for fast, energy-efficient neuromorphic computing. Proceedings of the National Academy of Sciences. 2016. P. 201604850.
5. Adrian E. D. The basis of sensation. W. W. Norton & Co, 1928.
6. Morrison A., Diesmann M., and Gerstner W. Phenomenological models of synaptic plasticity based on spike timing. Biological Cybernetics. 2008. V. 98. P. 459–478.
7. Peter U. Diehl and Matthew Cook. Unsupervised learning of digit recognition using Spike-Timing-Dependent Plasticity. Frontiers in Computational Neuroscience, 2015.
8. Сбоев А. Г. Сравнение частотного и временного кодирования данных при решении спайковой сетью со Spike-Timing-Dependent Plasticity: задачи классификации / А. Г. Сбоев [и др.] // Вестник национального исследовательского ядерного университета МИФИ. – 2018. – Т. 7 (6). – С. 563–568.
9. Richard Kempter, Wulfram Gerstner, and J. Leo van Hemmen. Intrinsic stabilization of output rates by spike-based hebbian learning. Neural computation. 2001. V. 13 (12). P. 2709–2741.
10. Eugene M. Izhikevich and Niraj S. Desai. Relating STDP to BCM. Neural computation. 2003. V. 15 (7). P. 1511–1523.
11. Sboev A., Rybka R., and Serenko A. On the effect of stabilizing mean firing rate of a neuron due to STDP. In J. Kortelainen, A. Bilyatdinova, A. Klimova, and A. Boukhanovsky, editors, 6th International Young Scientist Conference on Computational Science. Elsevier BV, 2017. V. 119. P. 166–173.
12. Mark C. W. van Rossum, Guo Qiang Bi, and Gina G. Turrigiano. Stable Hebbian learning from Spike Timing-Dependent Plasticity. Journal of neuroscience. 2000. V. 20 (23). P. 8812–8821.
13. Sen Song, Kenneth D. Miller, and Larry F. Abbott. Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience. 2000. V. 3 (9). P. 919–926.
14. Sboev A., Rybka R., Serenko A., Vlasov D., Kudryashov N., and Demin V. To the role of the choice of the neuron model in spiking network learning on base of Spike-Timing-Dependent Plasticity. In V. V. Klimov and A. V. Samsonovich, editors, 8th Annual International Conference on Biologically Inspired Cognitive Architectures. Elsevier BV, 2018. V. 123. P. 432–439.
15. Susanne Kunkel, Abigail Morrison, Philipp Weidel, Jochen Martin Eppler, Ankur Sinha, Wolfram Schenck, Maximilian Schmidt, Stine Brekke Vennemo, Jakob Jordan, Alexander Peyser, Dimitri Plotnikov, Steffen Graber, Tanguy Fardet, Dennis Terhorst, Håkon Mørk, Guido Trensch, Alex Seeholzer, Rajalekshmi Deepu, Jan Hahne, Inga Blundell, Tammo Ippen, Jannis Schuecker, Hannah Bos, Sandra Diaz, Espen Hagen, Sepehr Mahmoudian, Claudia Bachmann, Mikkel Elle Lepperød, Oliver Breitwieser, Bruno Golosio, Hendrik Rothe, Hesam Setareh, Mikael Djurfeldt, Till Schumann, Alexey Shusharin, Jes´us Garrido, Eilif Benjamin Muller, Arjun Rao, Juan Hernando Vieites, and Hans Ekkehard Plesser. NEST 2.12.0, March 2017.
Рецензия
Для цитирования:
Сбоев А.Г., Рыбка Р.Б., Серенко А.В. Влияние корреляции спайковых последовательностей на обучение нейронной сети под действием Spike-Timing-Dependent Plasticity. Вестник НИЯУ МИФИ. 2020;9(1):82-90. https://doi.org/10.1134/S2304487X20010083
For citation:
Sboev A.G., Rybka R.B., Serenko A.V. Effect of Spike Train Correlation on Spiking Neural Network Learning by Spike-Timing-Dependent Plasticity. Vestnik natsional'nogo issledovatel'skogo yadernogo universiteta "MIFI". 2020;9(1):82-90. (In Russ.) https://doi.org/10.1134/S2304487X20010083
Просмотров:
118
Послать статью по эл. почте 