Bayesian Inference With Muller C-Elements

Abstract

International audienceBayesian inference is a powerful approach for integrating independent conflicting information for decision-making. Though an important component of robotic, biological, and other sensory-motors systems, general-purpose computers perform Bayesian inference with limited efficiency. Here we show that Bayesian inference can be efficiently performed with stochastic signals, which are particularly adapted to novel low power nano-devices that exhibit faults and device variations. A simple Muller C-element directly implements Bayes' rule. Complex inferences are performed by C-element trees, which compute the probability of an event based on multiple independent sources of evidence. A naïve Bayesian spam filter circuit is demonstrated as a pedagogical application, and design techniques for improving circuit functionality are described. Limitations of this structure are discussed in terms of signal autocorrelation. The stochastic inference structure is exceptionally robust to faults, an essential feature of decision circuits, and can therefore leverage the increased efficiency of emerging nanodevices. This hardware implementation of Bayesian inference is extremely area and power efficient, with an area-energy-delay product several orders of magnitude less than the conventional floating point implementation. These results open a pathway for a direct stochastic hardware implementation of Bayesian inference, enabling a new class of embedded decision circuits for robotics and medical applications

Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing

“…S6). The outputs of these generators are then combined using C-Elements to perform an approximate Bayesian inference 3 . The time average of the output gives the probability of the presented message being spam.…”

“…Many of these emerging ideas, such as stochastic computing [2][3][4][5][6] and some brain-inspired (or neuromorphic) schemes [7][8][9] , require a large quantity of random numbers. However, the circuit area and the energy required to generate these random numbers are major limitations of such computing schemes.…”

Stochastic Memory Devices for Security and Computing

“…In all these applications, guaranteeing secure data-transmission is of paramount importance. Several emerging computing paradigms, such as stochastic [17,18,26] and brain-inspired computing, [19,20] also rely on large bitstreams of random analog/digital signals for their operation, thus requiring on-chip entropy sources. For implementation in resource constrained IoT systems, RNGs should be compact and reliable, while featuring high-quality entropy, high throughput, and low power consumption.…”

A Bayesian Stochastic Machine for Sound Source Localization

“…Since inference only uses these two types of operation on probability values, one can map any inference into a circuit by spatially organizing these devices on a silicon substrate. Friedman et al [13] used Muller C-Elements to combine stochastic signals and achieved naive Bayes fusion for binary random variables.…”