Experimental Demonstration of Array-level Learning with Phase Change Synaptic Devices

TL;DR

This paper demonstrates that 2-D arrays of phase change synaptic devices can perform associative learning and pattern recognition, showing robustness to device variations and scalability in training iterations.

Contribution

It provides the first hardware demonstration of array-level learning with phase change synaptic devices in a brain-inspired architecture.

Findings

Pattern recognition is robust against synaptic resistance variations.

Increasing training iterations can compensate for large device variations.

Device variation from 9% to 60% increases training iterations from 1 to 11.

Abstract

The computational performance of the biological brain has long attracted significant interest and has led to inspirations in operating principles, algorithms, and architectures for computing and signal processing. In this work, we focus on hardware implementation of brain-like learning in a brain-inspired architecture. We demonstrate, in hardware, that 2-D crossbar arrays of phase change synaptic devices can achieve associative learning and perform pattern recognition. Device and array-level studies using an experimental 10x10 array of phase change synaptic devices have shown that pattern recognition is robust against synaptic resistance variations and large variations can be tolerated by increasing the number of training iterations. Our measurements show that increase in initial variation from 9 % to 60 % causes required training iterations to increase from 1 to 11.