Building fast Bayesian computing machines out of intentionally stochastic, digital parts

02/20/2014
by   Vikash Mansinghka, et al.
0

The brain interprets ambiguous sensory information faster and more reliably than modern computers, using neurons that are slower and less reliable than logic gates. But Bayesian inference, which underpins many computational models of perception and cognition, appears computationally challenging even given modern transistor speeds and energy budgets. The computational principles and structures needed to narrow this gap are unknown. Here we show how to build fast Bayesian computing machines using intentionally stochastic, digital parts, narrowing this efficiency gap by multiple orders of magnitude. We find that by connecting stochastic digital components according to simple mathematical rules, one can build massively parallel, low precision circuits that solve Bayesian inference problems and are compatible with the Poisson firing statistics of cortical neurons. We evaluate circuits for depth and motion perception, perceptual learning and causal reasoning, each performing inference over 10,000+ latent variables in real time - a 1,000x speed advantage over commodity microprocessors. These results suggest a new role for randomness in the engineering and reverse-engineering of intelligent computation.

READ FULL TEXT

page 1

page 17

page 21

page 23

page 25

page 27

research
02/19/2019

SPINBIS: Spintronics based Bayesian Inference System with Stochastic Computing

Bayesian inference is an effective approach for solving statistical lear...
research
11/03/2017

Spintronics based Stochastic Computing for Efficient Bayesian Inference System

Bayesian inference is an effective approach for solving statistical lear...
research
07/01/2015

Energy-efficient neuromorphic classifiers

Neuromorphic engineering combines the architectural and computational pr...
research
09/14/2016

Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals

Reconstruction of the tridimensional geometry of a visual scene using th...
research
09/14/2019

Rapid Bayesian inference for expensive stochastic models

Almost all fields of science rely upon statistical inference to estimate...
research
09/22/2017

Approximate Bayesian Inference in Linear State Space Models for Intermittent Demand Forecasting at Scale

We present a scalable and robust Bayesian inference method for linear st...
research
11/09/2022

In-memory factorization of holographic perceptual representations

Disentanglement of constituent factors of a sensory signal is central to...

Please sign up or login with your details

Forgot password? Click here to reset