Unsupervised Learning of Digit Recognition Through Spike-Timing-Dependent Plasticity Based on Memristors

Abstract

Neuromorphic computing based on spiking neural networks (SNNs) is a promising alternative in the field of intelligent computing, especially when traditional Von Neumann architectures is facing several choke point. Memristors, as the fourth-generation fundamental circuit element, play a crucial role in neuromorphic computing systems and are commonly employed as neural and synaptic devices. Due to their spike-based operation, memristive spiking neural networks (MSNNs) are considered to be superior and biologically plausible compared to alternative systems in terms of effectiveness. Here, the spike-timing-dependent plasticity (STDP) learning characteristic is reaped from our manufactured equipment. Utilizing memristor-based leaky integrate-and-fire (LIF) neurons and synapses, unsupervised learning of spiking neural networks with 784 × 324 × 324 architectures are constructed.