Uncertainty Reasoning with Photonic Bayesian Machines

TL;DR

This paper introduces a photonic Bayesian machine that uses chaotic light sources for fast, uncertainty-aware AI, capable of classification and out-of-domain detection in medical imaging.

Contribution

It presents a novel photonic hardware platform for Bayesian neural networks that significantly accelerates probabilistic computations and uncertainty reasoning.

Findings

Achieves 37.5 ps per convolution processing speed.

Demonstrates effective classification and out-of-domain detection.

Enables high-speed trustworthy AI with reduced sampling costs.

Abstract

Artificial intelligence (AI) systems increasingly influence safety-critical aspects of society, from medical diagnosis to autonomous mobility, making uncertainty awareness a central requirement for trustworthy AI. We present a photonic Bayesian machine that leverages the inherent randomness of chaotic light sources to enable uncertainty reasoning within the framework of Bayesian Neural Networks. The analog processor features a 1.28 Tbit/s digital interface compatible with PyTorch, enabling probabilistic convolutions processing within 37.5 ps per convolution. We use the system for simultaneous classification and out-of-domain detection of blood cell microscope images and demonstrate reasoning between aleatoric and epistemic uncertainties. The photonic Bayesian machine removes the bottleneck of pseudo random number generation in digital systems, minimizes the cost of sampling for probabilistic models, and thus enables high-speed trustworthy AI systems.