Unsupervised Online Learning With Multiple Postsynaptic Neurons Based on Spike-Timing-Dependent Plasticity Using a TFT-Type NOR Flash Memory Array

TL;DR

This paper introduces a neuromorphic system using TFT-type NOR flash memory for unsupervised online learning with multiple POST neurons based on STDP, successfully recognizing handwritten digits without preprocessing.

Contribution

It presents a novel two-layer neuromorphic architecture with multiple POST neurons and demonstrates unsupervised learning on MNIST using a TFT-type NOR flash memory array.

Findings

Achieved unsupervised digit recognition with STDP on MNIST

Showed the impact of POST neuron number on recognition rate

Utilized lateral inhibition and homeostasis for competitive learning

Abstract

We present a two-layer fully connected neuromorphic system based on a thin-film transistor (TFT)-type NOR flash memory array with multiple postsynaptic (POST) neurons. Unsupervised online learning by spike-timing-dependent plasticity (STDP) on the binary MNIST handwritten datasets is implemented, and its recognition result is determined by measuring firing rate of POST neurons. Using a proposed learning scheme, we investigate the impact of the number of POST neurons in terms of recognition rate. In this neuromorphic system, lateral inhibition function and homeostatic property are exploited for competitive learning of multiple POST neurons. The simulation results demonstrate unsupervised online learning of the full black-and-white MNIST handwritten digits by STDP, which indicates the performance of pattern recognition and classification without preprocessing of input patterns.