Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks
Open Access
- 20 November 2023
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-13
Abstract
Safety-critical sensory applications, like medical diagnosis, demand accurate decisions from limited, noisy data. Bayesian neural networks excel at such tasks, offering predictive uncertainty assessment. However, because of their probabilistic nature, they are computationally intensive. An innovative solution utilizes memristors’ inherent probabilistic nature to implement Bayesian neural networks. However, when using memristors, statistical effects follow the laws of device physics, whereas in Bayesian neural networks, those effects can take arbitrary shapes. This work overcome this difficulty by adopting a variational inference training augmented by a “technological loss”, incorporating memristor physics. This technique enabled programming a Bayesian neural network on 75 crossbar arrays of 1,024 memristors, incorporating CMOS periphery for in-memory computing. The experimental neural network classified heartbeats with high accuracy, and estimated the certainty of its predictions. The results reveal orders-of-magnitude improvement in inference energy efficiency compared to a microcontroller or an embedded graphics processing unit performing the same task.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Implementing Bayesian networks with embedded stochastic MRAMAIP Advances, 2018
- Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional ComputingPhysical Review Applied, 2017
- Variational Inference: A Review for StatisticiansJournal of the American Statistical Association, 2017
- Bayesian Inference With Muller C-ElementsIEEE Transactions on Circuits and Systems I: Regular Papers, 2016
- Probabilistic machine learning and artificial intelligenceNature, 2015
- Training and operation of an integrated neuromorphic network based on metal-oxide memristorsNature, 2015
- Set Variability and Failure Induced by Complementary Switching in Bipolar RRAMIEEE Electron Device Letters, 2013
- Statistics of Resistance Drift Due to Structural Relaxation in Phase-Change Memory ArraysIEEE Transactions on Electron Devices, 2010
- Aleatory or epistemic? Does it matter?Structural Safety, 2009
- PhysioNet: a Web-based resource for the study of physiologic signalsIEEE Engineering in Medicine and Biology Magazine, 2001