Improving Robustness of ReRAM-based Spiking Neural Network Accelerator with Stochastic Spike-timing-dependent-plasticity

TL;DR

This paper introduces a stochastic STDP algorithm for ReRAM-based SNN accelerators that improves robustness against input noise and device variation, enhancing accuracy and reliability.

Contribution

The paper proposes a novel stochastic STDP algorithm that dynamically adjusts synaptic behavior using spiking frequency, improving robustness in noisy environments and device variations.

Findings

Accuracy improved over deterministic STDP in noisy pattern recognition tasks.

The algorithm enhances resilience of ReRAM-based SNN accelerators to device variation.

Demonstrates effective robustness in real-world noisy conditions.

Abstract

Spike-timing-dependent-plasticity (STDP) is an unsupervised learning algorithm for spiking neural network (SNN), which promises to achieve deeper understanding of human brain and more powerful artificial intelligence. While conventional computing system fails to simulate SNN efficiently, process-in-memory (PIM) based on devices such as ReRAM can be used in designing fast and efficient STDP based SNN accelerators, as it operates in high resemblance with biological neural network. However, the real-life implementation of such design still suffers from impact of input noise and device variation. In this work, we present a novel stochastic STDP algorithm that uses spiking frequency information to dynamically adjust synaptic behavior. The algorithm is tested in pattern recognition task with noisy input and shows accuracy improvement over deterministic STDP. In addition, we show that the new algorithm can be used for designing a robust ReRAM based SNN accelerator that has strong resilience to device variation.