# ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing

## TL;DR

ReStoCNet is a memory-efficient residual stochastic binary convolutional spiking neural network that uses a novel unsupervised learning algorithm, achieving high accuracy with significantly reduced memory footprint on pattern recognition tasks.

## Contribution

The paper introduces ReStoCNet, a deep residual binary SNN with a new HB-STDP learning rule, enabling efficient memory use and improved feature learning.

## Key findings

- Over 20x kernel memory compression compared to full-precision SNNs.
- Residual connections improve deep SNN accuracy on MNIST and CIFAR-10.
- HB-STDP enables layer-wise unsupervised training of binary kernels.

## Abstract

In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature learning capability of deep SNNs. We propose Spike Timing Dependent Plasticity (STDP) based probabilistic learning algorithm, referred to as Hybrid-STDP (HB-STDP), incorporating Hebbian and anti-Hebbian learning mechanisms, to train the binary kernels forming ReStoCNet in a layer-wise unsupervised manner. We demonstrate the efficacy of ReStoCNet and the presented HB-STDP based unsupervised training methodology on the MNIST and CIFAR-10 datasets. We show that residual connections enable the deeper convolutional layers to self-learn useful high-level input features and mitigate the accuracy loss observed in deep SNNs devoid of residual connections. The proposed ReStoCNet offers >20x kernel memory compression compared to full-precision (32-bit) SNN while yielding high enough classification accuracy on the chosen pattern recognition tasks.