An Energy-Efficient Bayesian Neural Network Implementation Using Stochastic Computing Method
- 3 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (9) , 12913-12923
Abstract
The robustness of Bayesian neural networks (BNNs) to real-world uncertainties and incompleteness has led to their application in some safety-critical fields. However, evaluating uncertainty during BNN inference requires repeated sampling and feed-forward computing, making them challenging to deploy in low-power or embedded devices. This article proposes the use of stochastic computing (SC) to optimize the hardware performance of BNN inference in terms of energy consumption and hardware utilization. The proposed approach adopts bitstream to represent Gaussian random number and applies it in the inference phase. This allows for the omission of complex transformation computations in the central limit theorem-based Gaussian random number generating (CLT-based GRNG) method and the simplification of multipliers as and operations. Furthermore, an asynchronous parallel pipeline calculation technique is proposed in computing block to enhance operation speed. Compared with conventional binary radix-based BNN, SC-based BNN (StocBNN) realized by FPGA with 128-bit bitstream consumes much less energy consumption and hardware resources with less than 0.1% accuracy decrease when dealing with MNIST/Fashion-MNIST datasets.Keywords
Funding Information
- National Natural Science Foundation of China (62006011, U20A20204, 62072019, 62004011)
- 111 talent program (B16001)
This publication has 37 references indexed in Scilit:
- A Survey on Deep LearningACM Computing Surveys, 2018
- A Stochastic Computational Multi-Layer Perceptron with Backward PropagationIEEE Transactions on Computers, 2018
- Deep Learning in Microscopy Image Analysis: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2017
- Why Does Deep and Cheap Learning Work So Well?Journal of Statistical Physics, 2017
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- Gaussian Random Number GenerationACM Computing Surveys, 2016
- Bayesian Recurrent Neural Network for Language ModelingIEEE Transactions on Neural Networks and Learning Systems, 2015
- A New Stochastic Computing Methodology for Efficient Neural Network ImplementationIEEE Transactions on Neural Networks and Learning Systems, 2015
- A Bayesian regularized artificial neural network for stock market forecastingExpert Systems with Applications, 2013
- Survey of Stochastic ComputingACM Transactions on Embedded Computing Systems, 2013