34 citations · 162 across the 24 of their papers we have counts for
3 papers · 1 filter
Universality of physical neural networks with multivariate nonlinearity
Benjamin Savinson, David J. Norris, Siddhartha Mishra +1
The enormous energy demand of artificial intelligence is driving the development of alternative hardware for deep learning. Physical neural networks try to exploit physical systems…
Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI
Bogdan Raonić, Siddhartha Mishra, Samuel Lanthaler
Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out-of-distribution (OOD) data, but…
Theory-to-Practice Gap for Neural Networks and Neural Operators
Philipp Grohs, Samuel Lanthaler, Margaret Trautner
This work studies the sampling complexity of learning with ReLU neural networks and neural operators. For mappings belonging to relevant approximation spaces, we derive upper bound…