An Online Learning Algorithm for Neuromorphic Hardware Implementation

We propose a sign-based online learning (SOL) algorithm for a neuromorphic hardware framework called Trainable Analogue Block (TAB). The TAB framework utilises the principles of neural population coding, implying that it encodes the input stimulus using a large pool of nonlinear neurons. The SOL algorithm is a simple weight update rule that employs the sign of the hidden layer activation and the sign of the output error, which is the difference between the target output and the predicted output. The SOL algorithm is easily implementable in hardware, and can be used in any artificial neural network framework that learns weights by minimising a convex cost function. We show that the TAB framework can be trained for various regression tasks using the SOL algorithm.

[1]  ISMAEL FERRUSQUÍA-VILLAFRANCA,et al.  Chapter 13 , 2003, Dear Kamala.

[2]  Xilinx Family.  Efficient Shift Registers, LFSR Counters, and Long Pseudo- Random Sequence Generators , 1996 .

[3]  Shihab A. Shamma,et al.  Sound stream segregation: a neuromorphic approach to solve the “cocktail party problem” in real-time , 2015, Front. Neurosci..

[4]  Dewen Hu,et al.  Multiobjective Reinforcement Learning: A Comprehensive Overview , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[5]  André van Schaik,et al.  Live demonstration: FPGA implementation of the CAR model of the cochlea , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[6]  Richard E. Brown,et al.  Report to Congress on Server and Data Center Energy Efficiency: Public Law 109-431 , 2008 .

[7]  André van Schaik,et al.  Learning the pseudoinverse solution to network weights , 2012, Neural Networks.

[8]  André van Schaik,et al.  A neuromorphic hardware framework based on population coding , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[9]  D. Kalman.  A Singularly Valuable Decomposition: The SVD of a Matrix , 1996 .

[10]  Tingwen Huang,et al.  A Spintronic Memristor-Based Neural Network With Radial Basis Function for Robotic Manipulator Control Implementation , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[11]  Alexander S. Ecker,et al.  The Effect of Noise Correlations in Populations of Diversely Tuned Neurons , 2011, The Journal of Neuroscience.

[12]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[13]  Naoyuki Kubota,et al.  Biologically Inspired Control System for 3-D Locomotion of a Humanoid Biped Robot , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[14]  R. Sathya,et al.  Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification , 2013 .

[15]  André van Schaik,et al.  A mixed-signal implementation of a polychronous spiking neural network with delay adaptation , 2014, Front. Neurosci..

[16]  Michael I. Jordan,et al.  A more biologically plausible learning rule for neural networks. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[17]  André van Schaik,et al.  A Low Power Trainable Neuromorphic Integrated Circuit That Is Tolerant to Device Mismatch , 2016, IEEE Transactions on Circuits and Systems I: Regular Papers.

[18]  Léon Bottou,et al.  The Tradeoffs of Large Scale Learning , 2007, NIPS.

[19]  André van Schaik,et al.  FPGA implementation of the CAR Model of the cochlea , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[20]  André van Schaik,et al.  A neuromorphic implementation of multiple spike-timing synaptic plasticity rules for large-scale neural networks , 2015, Front. Neurosci..

[21]  Gregory Cohen,et al.  Synthesis of neural networks for spatio-temporal spike pattern recognition and processing , 2013, Front. Neurosci..

[22]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[23]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Peter Alfke,et al.  Efficient Shift Registers, LFSR Counters, and Long Pseudo Random Sequence Generators , 1995 .

[25]  Bagrat Amirikian,et al.  Directional tuning profiles of motor cortical cells , 2000, Neuroscience Research.

[26]  T. Sejnowski.  Neural populations revealed , 1988, Nature.

[27]  André van Schaik,et al.  Neuromorphic Hardware Architecture Using the Neural Engineering Framework for Pattern Recognition , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[28]  André van Schaik,et al.  Stochastic Electronics: A Neuro-Inspired Design Paradigm for Integrated Circuits , 2014, Proceedings of the IEEE.

[29]  Ali H. Sayed,et al.  Adaptive Filters , 2008 .

[30]  R. W. Lucky,et al.  Techniques for adaptive equalization of digital communication systems , 1966 .

[31]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.