Stimulus-induced sequential activity in supervisely trained recurrent networks of firing rate neurons

In this work, we consider recurrent neural networks of firing rate neurons supervisely trained to generate multidimensional sequences of given configurations. We study dynamical objects in the network multidimensional phase space underlying successfully trained outputs and analyze spatiotemporal neural activity and its features in three cases. First, we consider autonomous generation of complex sequences by output units driven by a recurrent network. Second, we study how input pulses can trigger different output units. Third, we explore the case where input pulses allow us to switch between different sequential activities of output units.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Lakhmi C. Jain,et al.  Recurrent Neural Networks: Design and Applications , 1999 .

[3]  B. McNaughton,et al.  Packet-based communication in the cortex , 2015, Nature Reviews Neuroscience.

[4]  R. Romo,et al.  A recurrent network model of somatosensory parametric working memory in the prefrontal cortex. , 2003, Cerebral cortex.

[5]  Zhang Yi,et al.  Multistability Analysis for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions , 2003, Neural Computation.

[6]  L. F. Abbott,et al.  Building functional networks of spiking model neurons , 2016, Nature Neuroscience.

[7]  Jianhong Wu,et al.  Multistability in Spiking Neuron Models of Delayed Recurrent Inhibitory Loops , 2007, Neural Computation.

[8]  L. F. Abbott,et al.  Generating Coherent Patterns of Activity from Chaotic Neural Networks , 2009, Neuron.

[9]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[10]  Omri Barak,et al.  Recurrent neural networks as versatile tools of neuroscience research , 2017, Current Opinion in Neurobiology.

[11]  Christopher Kim,et al.  Learning recurrent dynamics in spiking networks , 2018, bioRxiv.

[12]  M. Tsodyks,et al.  Synaptic Theory of Working Memory , 2008, Science.

[13]  Andrew M. Clark,et al.  Stimulus onset quenches neural variability: a widespread cortical phenomenon , 2010, Nature Neuroscience.

[14]  Konrad P. Körding,et al.  Toward an Integration of Deep Learning and Neuroscience , 2016, bioRxiv.

[15]  Guangyu R. Yang,et al.  Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework , 2016, PLoS Comput. Biol..

[16]  R. Douglas,et al.  A functional microcircuit for cat visual cortex. , 1991, The Journal of physiology.

[17]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[18]  L. Abbott,et al.  Eigenvalue spectra of random matrices for neural networks. , 2006, Physical review letters.

[19]  S. Strogatz,et al.  Chimera states for coupled oscillators. , 2004, Physical review letters.

[20]  Wojciech Zaremba,et al.  Recurrent Neural Network Regularization , 2014, ArXiv.

[21]  W. Maass,et al.  State-dependent computations: spatiotemporal processing in cortical networks , 2009, Nature Reviews Neuroscience.

[22]  Thomas Wennekers,et al.  Associative memory in networks of spiking neurons , 2001, Neural Networks.

[23]  Benjamin Schrauwen,et al.  The Introduction of Time-Scales in Reservoir Computing, Applied to Isolated Digits Recognition , 2007, ICANN.

[24]  Francesca Mastrogiuseppe,et al.  Linking Connectivity, Dynamics, and Computations in Low-Rank Recurrent Neural Networks , 2017, Neuron.

[25]  Vladimir I. Nekorkin,et al.  Dynamics of spiking map-based neural networks in problems of supervised learning , 2020, Commun. Nonlinear Sci. Numer. Simul..

[26]  Marcus Rohrbach,et al.  Translating Videos to Natural Language Using Deep Recurrent Neural Networks , 2014, NAACL.

[27]  Eva Kaslik,et al.  Impulsive hybrid discrete-time Hopfield neural networks with delays and multistability analysis , 2011, Neural Networks.

[28]  Christopher D. Harvey,et al.  Recurrent Network Models of Sequence Generation and Memory , 2016, Neuron.

[29]  Oleg V Maslennikov,et al.  Collective dynamics of rate neurons for supervised learning in a reservoir computing system. , 2019, Chaos.

[30]  David Sussillo,et al.  Neural circuits as computational dynamical systems , 2014, Current Opinion in Neurobiology.

[31]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[32]  G. Edelman,et al.  Large-scale model of mammalian thalamocortical systems , 2008, Proceedings of the National Academy of Sciences.

[33]  Jürgen Schmidhuber,et al.  Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks , 2008, NIPS.

[34]  Filip Ponulak,et al.  Introduction to spiking neural networks: Information processing, learning and applications. , 2011, Acta neurobiologiae experimentalis.

[35]  Benjamin Schrauwen,et al.  An overview of reservoir computing: theory, applications and implementations , 2007, ESANN.

[36]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[37]  CHIH-WEN SHIH,et al.  Multistability in Recurrent Neural Networks , 2006, SIAM J. Appl. Math..

[38]  Alexander Rivkind,et al.  Local Dynamics in Trained Recurrent Neural Networks. , 2015, Physical review letters.

[39]  L. F. Abbott,et al.  full-FORCE: A target-based method for training recurrent networks , 2017, PloS one.

[40]  David Sussillo,et al.  Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural Networks , 2013, Neural Computation.

[41]  Alireza Sadeghian,et al.  A bidirectional associative memory based on cortical spiking neurons using temporal coding , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[42]  Daniel J. Amit,et al.  Spike-Driven Synaptic Dynamics Generating Working Memory States , 2003, Neural Computation.

[43]  Ilya Sutskever,et al.  Learning Recurrent Neural Networks with Hessian-Free Optimization , 2011, ICML.

[44]  Wilten Nicola,et al.  Supervised learning in spiking neural networks with FORCE training , 2016, Nature Communications.

[45]  Vladimir I Nekorkin,et al.  Itinerant chimeras in an adaptive network of pulse-coupled oscillators. , 2018, Physical review. E.

[46]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[47]  Sommers,et al.  Chaos in random neural networks. , 1988, Physical review letters.

[48]  Henry Markram,et al.  Slow oscillations in neural networks with facilitating synapses , 2008, Journal of Computational Neuroscience.

[49]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[50]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[51]  Razvan Pascanu,et al.  Advances in optimizing recurrent networks , 2012, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[52]  Wolfgang Maass,et al.  Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning. , 2014, Cerebral cortex.

[53]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[54]  Francesca Mastrogiuseppe,et al.  Dynamics of random recurrent networks with correlated low-rank structure , 2019, 1909.04358.

[55]  G. Benettin,et al.  Lyapunov Characteristic Exponents for smooth dynamical systems and for hamiltonian systems; a method for computing all of them. Part 1: Theory , 1980 .

[56]  Benjamin Schrauwen,et al.  Reservoir Computing Trends , 2012, KI - Künstliche Intelligenz.

[57]  W. Newsome,et al.  Context-dependent computation by recurrent dynamics in prefrontal cortex , 2013, Nature.

[58]  D. Abrams,et al.  Chimera states: coexistence of coherence and incoherence in networks of coupled oscillators , 2014, 1403.6204.

[59]  L. Abbott,et al.  Stimulus-dependent suppression of chaos in recurrent neural networks. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[60]  Wulfram Gerstner,et al.  Associative memory in a network of ‘spiking’ neurons , 1992 .

[61]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[62]  Dean V. Buonomano,et al.  ROBUST TIMING AND MOTOR PATTERNS BY TAMING CHAOS IN RECURRENT NEURAL NETWORKS , 2012, Nature Neuroscience.

[63]  Botond Szatmáry,et al.  Spike-Timing Theory of Working Memory , 2010, PLoS Comput. Biol..

[64]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[65]  G. Buzsáki.  Rhythms of the brain , 2006 .