SWAT: A Spiking Neural Network Training Algorithm for Classification Problems

Abstract

Abstract-This paper presents a synaptic weight association training (SWAT) algorithm for spiking neural networks (SNNs). SWAT merges the Bienenstock-Cooper-Munro (BCM) learning rule with spike timing dependent plasticity (STDP). The STDP/BCM rule yields a unimodal weight distribution where the height of the plasticity window associated with STDP is modulated causing stability after a period of training. The SNN uses a single training neuron in the training phase where data associated with all classes is passed to this neuron. The rule then maps weights to the classifying output neurons to reflect similarities in the data across the classes. The SNN also includes both excitatory and inhibitory facilitating synapses which create a frequency routing capability allowing the information presented to the network to be routed to different hidden layer neurons. A variable neuron threshold level simulates the refractory period. SWAT is initially benchmarked against the nonlinearly separable Iris and Wisconsin Breast Cancer datasets. Results presented show that the proposed training algorithm exhibits a convergence accuracy of 95.5% and 96.2% for the Iris and Wisconsin training sets, respectively, and 95.3% and 96.7% for the testing sets, noise experiments show that SWAT has a good generalization capability. SWAT is also benchmarked using an isolated digit automatic speech recognition (ASR) system where a subset of the TI46 speech corpus is used. Results show that with SWAT as the classifier, the ASR system provides an accuracy of 98.875% for training and 95.25% for testing.Index Terms-Automatic speech recognition, BienenstockCooper-Munro, dynamic synapses, spike timing dependent plasticity, spiking neural networks.

A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks

“…STDP is controlled by relative preand postsynaptic spike times. Equation (6) specifies that postsynaptic spikes which follow presynaptic spikes cause the synaptic weight to be increased (LTP) and in contrast, synapses are weakened when presynaptic spike occurs after postsynaptic spike generation time (LTD).…”

“…Spiking neurons and adaptive synapses between neurons contribute to a new approach in cognition, decision making, and learning [4][5][6][7][8].…”

An Efficient Hardware Architecture for Multilayer Spiking Neural Networks

“…All the LTAs use the packets to transmit the information [4]. The rate encoding scheme is used in this paper, and the SNN can be trained using the learning algorithm in previous work [11]. The Xilinx Zynq-7000 development board (with a XC7Z020-CLG484 FPGA device) is used as the hardware platform.…”

IRIS Recognition System using Neural Network and Genetic Algorithm

“…What is important in developing neural networks is their useful behavior by learning to recognize and apply relationships between objects and patterns of objects specific to the real world. In this respect neural networks are tools that can be used to solve difficult problems [8], [9], [10]. Artificial neural networks are inspired by the architecture of the biological nervous system, which consists of a large number of relatively simple neurons that work in parallel to facilitate rapid decision-making [11].…”