Neural sampling machine with stochastic synapse allows brain-like learning and inference.
Nat Commun
; 13(1): 2571, 2022 05 11.
Article
em En
| MEDLINE
| ID: mdl-35546144
ABSTRACT
Many real-world mission-critical applications require continual online learning from noisy data and real-time decision making with a defined confidence level. Brain-inspired probabilistic models of neural network can explicitly handle the uncertainty in data and allow adaptive learning on the fly. However, their implementation in a compact, low-power hardware remains a challenge. In this work, we introduce a novel hardware fabric that can implement a new class of stochastic neural network called Neural Sampling Machine (NSM) by exploiting the stochasticity in the synaptic connections for approximate Bayesian inference. We experimentally demonstrate an in silico hybrid stochastic synapse by pairing a ferroelectric field-effect transistor (FeFET)-based analog weight cell with a two-terminal stochastic selector element. We show that the stochastic switching characteristic of the selector between the insulator and the metallic states resembles the multiplicative synaptic noise of the NSM. We perform network-level simulations to highlight the salient features offered by the stochastic NSM such as performing autonomous weight normalization for continual online learning and Bayesian inferencing. We show that the stochastic NSM can not only perform highly accurate image classification with 98.25% accuracy on standard MNIST dataset, but also estimate the uncertainty in prediction (measured in terms of the entropy of prediction) when the digits of the MNIST dataset are rotated. Building such a probabilistic hardware platform that can support neuroscience inspired models can enhance the learning and inference capability of the current artificial intelligence (AI).
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Inteligência Artificial
/
Redes Neurais de Computação
Tipo de estudo:
Prognostic_studies
Idioma:
En
Revista:
Nat Commun
Assunto da revista:
BIOLOGIA
/
CIENCIA
Ano de publicação:
2022
Tipo de documento:
Article
País de afiliação:
Estados Unidos