logo
ResearchBunny Logo
Neural sampling machine with stochastic synapse allows brain-like learning and inference

Engineering and Technology

Neural sampling machine with stochastic synapse allows brain-like learning and inference

S. Dutta, G. Detorakis, et al.

Discover the groundbreaking Neural Sampling Machine (NSM) designed to leverage stochastic synaptic connections for approximate Bayesian inference, achieving an impressive 98.25% accuracy on MNIST image classification. This innovative hardware is the result of collaborative research by Sourav Dutta, Georgios Detorakis, Abhishek Khanna, Benjamin Grisafe, Emre Neftci, and Suman Datta.

00:00
00:00
Playback language: English
Abstract
This paper introduces a novel hardware fabric implementing a stochastic neural network called the Neural Sampling Machine (NSM) using stochasticity in synaptic connections for approximate Bayesian inference. A hybrid stochastic synapse, pairing a ferroelectric field-effect transistor (FeFET)-based analog weight cell with a stochastic selector element, is demonstrated. Network simulations show the NSM's ability for autonomous weight normalization in continual online learning and Bayesian inferencing, achieving 98.25% accuracy on MNIST image classification and estimating prediction uncertainty.
Publisher
Nature Communications
Published On
May 11, 2022
Authors
Sourav Dutta, Georgios Detorakis, Abhishek Khanna, Benjamin Grisafe, Emre Neftci, Suman Datta
Tags
Neural Sampling Machine
stochastic neural networks
Bayesian inference
stochastic synapse
online learning
MNIST classification
prediction uncertainty

Related Publications

Explore these studies to deepen your understanding of the subject.

A wearable sensor and machine learning estimate step length in older adults and patients with neurological disorders
Medicine and Health

A wearable sensor and machine learning estimate step length in older adults and patients with neurological disorders

A. Zadka, N. Rabin, et al.

Divide-and-conquer: machine-learning integrates mammalian and viral traits with network features to predict virus-mammal associations
Veterinary Science

Divide-and-conquer: machine-learning integrates mammalian and viral traits with network features to predict virus-mammal associations

M. Wardeh, M. S. C. Blagrove, et al.

On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare
Computer Science

On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare

S. Mittal, K. Thakral, et al.

Radiogenomics for predicting p53 status, PD-L1 expression, and prognosis with machine learning in pancreatic cancer
Medicine and Health

Radiogenomics for predicting p53 status, PD-L1 expression, and prognosis with machine learning in pancreatic cancer

Y. Iwatate, I. Hoshino, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny