An Online Structural Plasticity Rule for Generating Better Reservoirs

In this letter, we propose a novel neuro-inspired low-resolution online unsupervised learning rule to train the reservoir or liquid of liquid state machines. The liquid is a sparsely interconnected huge recurrent network of spiking neurons. The proposed learning rule is inspired from structural plasticity and trains the liquid through formating and eliminating synaptic connections. Hence, the learning involves rewiring of the reservoir connections similar to structural plasticity observed in biological neural networks. The network connections can be stored as a connection matrix and updated in memory by using address event representation (AER) protocols, which are generally employed in neuromorphic systems. On investigating the pairwise separation property, we find that trained liquids provide 1.36 0.18 times more interclass separation while retaining similar intraclass separation as compared to random liquids. Moreover, analysis of the linear separation property reveals that trained liquids are 2.05 0.27 times better than random liquids. Furthermore, we show that our liquids are able to retain the generalization ability and generality of random liquids. A memory analysis shows that trained liquids have 83.67 5.79 ms longer fading memory than random liquids, which have shown 92.8 5.03 ms fading memory for a particular type of spike train inputs. We also throw some light on the dynamics of the evolution of recurrent connections within the liquid. Moreover, compared to separation-driven synaptic modification', a recently proposed algorithm for iteratively refining reservoirs, our learning rule provides 9.30%, 15.21%, and 12.52% more liquid separations and 2.8%, 9.1%, and 7.9% better classification accuracies for 4, 8, and 12 class pattern recognition tasks, respectively.

[1]  Stefan Schliebs,et al.  Constructing Robust Liquid State Machines to Process Highly Variable Data Streams , 2012, ICANN.

[2]  Subhrajit Roy,et al.  A current-mode spiking neural classifier with lumped dendritic nonlinearity , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[3]  B. Schrauwen,et al.  Isolated word recognition with the Liquid State Machine: a case study , 2005, Inf. Process. Lett..

[4]  Stefan Schliebs,et al.  Are probabilistic spiking neural networks suitable for reservoir computing? , 2011, The 2011 International Joint Conference on Neural Networks.

[5]  Masakazu Aono,et al.  A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing , 2013, Nanotechnology.

[6]  Jian-Xin Xu,et al.  Effects of synaptic connectivity on liquid state machine performance , 2013, Neural Networks.

[7]  S. Nelson,et al.  Multiple forms of short-term plasticity at excitatory synapses in rat medial prefrontal cortex. , 2000, Journal of neurophysiology.

[8]  Matthew Cook,et al.  Modeling the interplay between structural plasticity and spike-timing-dependent plasticity , 2015, BMC Neuroscience.

[9]  Bartlett W. Mel,et al.  Impact of Active Dendrites and Structural Plasticity on the Memory Capacity of Neural Tissue , 2001, Neuron.

[10]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

[11]  Subhrajit Roy,et al.  An Online Unsupervised Structural Plasticity Algorithm for Spiking Neural Networks , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Walter Senn,et al.  Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics , 2007, Neural Computation.

[13]  Oliver Obst,et al.  Taming the reservoir: Feedforward training for recurrent neural networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[14]  Panos E. Trahanias,et al.  Use of the separation property to derive Liquid State Machines with enhanced classification performance , 2013, Neurocomputing.

[15]  Wulfram Gerstner,et al.  Spiking Neuron Models: An Introduction , 2002 .

[16]  Grzegorz M. Wójcik.  Electrical parameters influence on the dynamics of the Hodgkin-Huxley liquid state machine , 2012, Neurocomputing.

[17]  Shaista Hussain,et al.  Hardware-Amenable Structural Learning for Spike-Based Pattern Classification Using a Simple Model of Active Dendrites , 2014, Neural Computation.

[18]  Marshall R. Mayberry,et al.  Critical branching neural computation , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[19]  Hananel Hazan,et al.  Topological constraints and robustness in liquid state machines , 2012, Expert Syst. Appl..

[20]  Qing Chen,et al.  The Critical Dynamics in Neural Network Improve the Computational Capability of Liquid State Machines , 2017, ISNN.

[21]  Shaista Hussain,et al.  Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines , 2013, 2013 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[22]  André Grüning,et al.  Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks , 2015, Neural Computation.

[23]  J. Deuchars,et al.  Single axon excitatory postsynaptic potentials in neocortical interneurons exhibit pronounced paired pulse facilitation , 1993, Neuroscience.

[24]  Éloi Bossé,et al.  Multistate combination approaches for liquid state machine in supervised spatiotemporal pattern classification , 2011, Neurocomputing.

[25]  André Grüning,et al.  Improved spike-timed mappings using a tri-phasic spike timing-dependent plasticity rule , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[26]  Dan Ventura,et al.  Improving liquid state machines through iterative refinement of the reservoir , 2010, Neurocomputing.

[27]  Robert A. Legenstein,et al.  Methods for Estimating the Computational Power and Generalization Capability of Neural Microcircuits , 2004, NIPS.

[28]  H. Markram,et al.  Redistribution of synaptic efficacy between neocortical pyramidal neurons , 1996, Nature.

[29]  Razvan V. Florian,et al.  The Chronotron: A Neuron That Learns to Fire Temporally Precise Spike Patterns , 2010, PloS one.

[30]  Ioana Sporea,et al.  Supervised Learning in Multilayer Spiking Neural Networks , 2012, Neural Computation.

[31]  David B. Grayden,et al.  Approximate, Computationally Efficient Online Learning in Bayesian Spiking Neurons , 2014, Neural Computation.

[32]  Giacomo Indiveri,et al.  Event-based softcore processor in a biohybrid setup applied to structural plasticity , 2015, 2015 International Conference on Event-based Control, Communication, and Signal Processing (EBCCSP).

[33]  L. Abbott,et al.  A Quantitative Description of Short-Term Plasticity at Excitatory Synapses in Layer 2/3 of Rat Primary Visual Cortex , 1997, The Journal of Neuroscience.

[34]  Kwabena Boahen,et al.  Learning in Silicon: Timing is Everything , 2005, NIPS.

[35]  Shaista Hussain,et al.  Learning Spike Time Codes Through Morphological Learning With Binary Synapses , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[36]  Fangzheng Xue,et al.  Computational capability of liquid state machines with spike-timing-dependent plasticity , 2013, Neurocomputing.

[37]  Alex Frid,et al.  Temporal pattern recognition via temporal networks of temporal neurons , 2012, 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel.

[38]  Subhrajit Roy,et al.  Liquid State Machine With Dendritically Enhanced Readout for Low-Power, Neuromorphic VLSI Implementations , 2014, IEEE Transactions on Biomedical Circuits and Systems.

[39]  Hyun-Chool Shin,et al.  Asynchronous Decoding of Dexterous Finger Movements Using M1 Neurons , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

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

[41]  Andrzej J. Kasinski,et al.  Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting , 2010, Neural Computation.

[42]  J. Hopfield,et al.  All-or-none potentiation at CA3-CA1 synapses. , 1998, Proceedings of the National Academy of Sciences of the United States of America.