Uncertainty Reasoning with Photonic Bayesian Machines
This work addresses the problem of enabling high-speed, trustworthy AI with uncertainty reasoning for applications such as medical diagnosis and autonomous mobility, representing a novel method rather than an incremental improvement.
The paper tackles the need for uncertainty-aware AI in safety-critical applications by presenting a photonic Bayesian machine that uses chaotic light sources for uncertainty reasoning, achieving 1.28 Tbit/s processing and 37.5 ps per convolution for tasks like blood cell image classification and out-of-domain detection.
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.