Dynamics of spiking map-based neural networks in problems of supervised learning

Abstract Recurrent networks of artificial spiking neurons trained to perform target functions are a perspective tool for understanding dynamic principles of information processing in computational neuroscience. Here, we develop a system of this type based on a map-based model of neural activity allowing for producing various biologically relevant regimes. Target signals used to supervisely train the network are sinusoid functions of different frequencies. Impacts of individual neuron dynamics, coupling strength, network size and other key parameters on the learning error are studied. Our findings suggest, among others, that firing rate heterogeneity as well as mixing of spiking and nonspiking regimes of neurons comprising the network can improve its performance for a wider range of target frequencies. At a single neuron activity level, successful training gives rise to well separated domains with qualitatively different dynamics.

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

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

[3]  Vladimir I. Nekorkin,et al.  Map-Based Approach to Problems of Spiking Neural Network Dynamics , 2014 .

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

[5]  Christian K. Machens,et al.  Predictive Coding of Dynamical Variables in Balanced Spiking Networks , 2013, PLoS Comput. Biol..

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

[7]  Oleg V Maslennikov,et al.  Transient sequences in a hypernetwork generated by an adaptive network of spiking neurons , 2017, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

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

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

[10]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[11]  Jürgen Kurths,et al.  Basin stability for burst synchronization in small-world networks of chaotic slow-fast oscillators. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  Wolfgang Maass,et al.  Liquid State Machines: Motivation, Theory, and Applications , 2010 .

[13]  V I Nekorkin,et al.  Chaotic oscillations in a map-based model of neural activity. , 2007, Chaos.

[14]  Matthew T. Kaufman,et al.  A neural network that finds a naturalistic solution for the production of muscle activity , 2015, Nature Neuroscience.

[15]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

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

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

[18]  Hilbert J. Kappen,et al.  Learning Universal Computations with Spikes , 2015, PLoS Comput. Biol..

[19]  Igor Franović,et al.  Mean-field dynamics of a population of stochastic map neurons. , 2017, Physical review. E.

[20]  Adrienne L Fairhall,et al.  Constructing Precisely Computing Networks with Biophysical Spiking Neurons , 2014, The Journal of Neuroscience.

[21]  Sophie Denève,et al.  Enforcing balance allows local supervised learning in spiking recurrent networks , 2015, NIPS.

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

[23]  Kaushik Roy,et al.  Towards spike-based machine intelligence with neuromorphic computing , 2019, Nature.

[24]  Yuan Zhao,et al.  Interpretable Nonlinear Dynamic Modeling of Neural Trajectories , 2016, NIPS.

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

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

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

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

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

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

[31]  Chris Eliasmith,et al.  Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems , 2004, IEEE Transactions on Neural Networks.

[32]  Vladimir I. Nekorkin,et al.  Map Based Models in Neurodynamics , 2010, Int. J. Bifurc. Chaos.

[33]  Michael Pfeiffer,et al.  Deep Learning With Spiking Neurons: Opportunities and Challenges , 2018, Front. Neurosci..

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

[35]  Oleg V Maslennikov,et al.  Modular networks with delayed coupling: synchronization and frequency control. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

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

[38]  Trevor Bekolay,et al.  A Large-Scale Model of the Functioning Brain , 2012, Science.

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

[40]  Peter Ford Dominey,et al.  Reservoir Computing Properties of Neural Dynamics in Prefrontal Cortex , 2016, PLoS Comput. Biol..

[41]  Vladimir I. Nekorkin,et al.  Discrete model of the olivo-cerebellar system: structure and dynamics , 2012 .

[42]  M. Sanjuán,et al.  Map-based models in neuronal dynamics , 2011 .

[43]  O. Kinouchi,et al.  A brief history of excitable map-based neurons and neural networks , 2013, Journal of Neuroscience Methods.