collaborators

7 papers

cs.LG2026

Constrained Co-Design for Photonic Bayesian Neural Networks

Hendrik Borras, Xiao Wang, Bernhard Klein +4

Classical neural networks frequently produce overconfident predictions on ambiguous or out-of-distribution (OOD) data, a liability that grows with each AI system deployed in safety…

physics.app-ph2026

Probabilistic Photonic Computing

Frank Brückerhoff-Plückelmann, Anna P. Ovvyan, Akhil Varri +8

Probabilistic computing excels in approximating combinatorial problems and modelling uncertainty. However, using conventional deterministic hardware for probabilistic models is cha…

cs.LG2025

Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification

Hendrik Borras, Yong Wu, Bernhard Klein +1

Bayesian Neural Networks (BNNs) provide principled uncertainty quantification but suffer from substantial computational and memory overhead compared to deterministic networks. Whil…

cs.LG2025

Uncertainty Reasoning with Photonic Bayesian Machines

F. Brückerhoff-Plückelmann, H. Borras, S. U. Hulyal +12

Artificial intelligence (AI) systems increasingly influence safety-critical aspects of society, from medical diagnosis to autonomous mobility, making uncertainty awareness a centra…

cs.LG2025

Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation

Bernhard Klein, Falk Selker, Hendrik Borras +3

Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handling restricts use in s…

cs.LG2025

Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations

Xiao Wang, Hendrik Borras, Bernhard Klein +1

The disparity between the computational demands of deep learning and the capabilities of compute hardware is expanding drastically. Although deep learning achieves remarkable perfo…