Sparsity-Aware Optimization of In-Memory Bayesian Binary Neural Network Accelerators

TL;DR

This paper introduces a sparsity-aware optimization for Bayesian Binary Neural Network accelerators that exploits sampling sparsity to significantly reduce resource consumption without sacrificing accuracy, enabling more efficient edge AI deployment.

Contribution

The paper proposes a novel sparsity-aware optimization scheme for BBNN accelerators that leverages inherent sampling sparsity to reduce resource usage by up to 86%, with no accuracy loss.

Findings

Up to 86% reduction in sampled parameters.

Up to 5.3x reduction in area and 8.8x in energy.

Achieves 2.9x higher power efficiency than state-of-the-art.

Abstract

Bayesian Neural Networks (BNNs) provide principled estimates of model and data uncertainty by encoding parameters as distributions. This makes them key enablers for reliable AI that can be deployed on safety critical edge systems. These systems can be made resource efficient by restricting synapses to two synaptic states $\{-1,+1\}$ and using a memristive in-memory computing (IMC) paradigm. However, BNNs pose an additional challenge -- they require multiple instantiations for ensembling, consuming extra resources in terms of energy and area. In this work, we propose a novel sparsity-aware optimization for Bayesian Binary Neural Network (BBNN) accelerators that exploits the inherent BBNN sampling sparsity -- most of the network is made up of synapses that have a high probability of being fixed at $\pm1$ and require no sampling. The optimization scheme proposed here exploits the sampling sparsity that exists both among layers, i.e only a few layers of the network contain a majority of the probabilistic synapses, as well as the parameters i.e., a tiny fraction of parameters in these layers require sampling, reducing total sampled parameter count further by up to $86\%$. We demonstrate no loss in accuracy or uncertainty quantification performance for a VGGBinaryConnect network on CIFAR-100 dataset mapped on a custom sparsity-aware phase change memory (PCM) based IMC simulator. We also develop a simple drift compensation technique to demonstrate robustness to drift-induced degradation. Finally, we project latency, energy, and area for sparsity-aware BNN implementation in both pipelined and non-pipelined modes. With sparsity-aware implementation, we estimate upto $5.3 \times$ reduction in area and $8.8\times$ reduction in energy compared to a non-sparsity-aware implementation. Our approach also results in $2.9 \times $ more power efficiency compared to the state-of-the-art BNN accelerator.