Wolfram Pernice, Münster University

Leuchs-Russell-Auditorium, A.1.500, Staudtstr. 2

Location details

Abstract:
Unlike artificial neural networks (ANNs), which focus on maximizing accuracy, biological systems excel at handling uncertainty. This ability is believed to be essential for adaptability and efficiency, yet traditional ANNs, implemented on deterministic hardware, struggle with capturing the full probabilistic nature of inference. To address this limitation, Bayesian neural networks (BNNs) replace deterministic parameters with probability distributions, allowing us to enable uncertainty quantification and out-of-distribution detection in cases of incomplete data. However, processing probabilistic models remains a challenge for conventional digital hardware, which relies on deterministic von Neumann architectures that operate far from physical noise.
To address these challenges, I will outline recent progress in photonic computing architectures that harness hardware noise as a computational resource rather than a constraint. Using amplitude-bandwidth encoding allows for processing probabilistic information in an in-memory computing fashion. In photonic crossbar arrays, we can achieve parallel probabilistic operations using chaotic light as a physical entropy source for random number generation. This approach paves the way for high-speed probabilistic machine learning beyond the limitations of conventional hardware.