A Stochastic Approach to STDP

TL;DR

This paper introduces a digital, stochastic method for implementing STDP that efficiently simulates exponential decay and scales to large neural networks in real time.

Contribution

It presents a novel stochastic approach to efficiently implement exponential decay in digital STDP, enabling large-scale, real-time neural network simulations.

Findings

Validated with balanced excitation/inhibition experiments

Achieves 8k virtual STDP adaptors with minimal hardware

Suitable for large-scale, real-time spiking neural networks

Abstract

We present a digital implementation of the Spike Timing Dependent Plasticity (STDP) learning rule. The proposed digital implementation consists of an exponential decay generator array and a STDP adaptor array. On the arrival of a pre- and post-synaptic spike, the STDP adaptor will send a digital spike to the decay generator. The decay generator will then generate an exponential decay, which will be used by the STDP adaptor to perform the weight adaption. The exponential decay, which is computational expensive, is efficiently implemented by using a novel stochastic approach, which we analyse and characterise here. We use a time multiplexing approach to achieve 8192 (8k) virtual STDP adaptors and decay generators with only one physical implementation of each. We have validated our stochastic STDP approach with measurement results of a balanced excitation/inhibition experiment. Our stochastic approach is ideal for implementing the STDP learning rule in large-scale spiking neural networks running in real time.