2 papers
cs.LG2024
Information Geometry of Evolution of Neural Network Parameters While Training
Abhiram Anand Thiruthummal, Eun-jin Kim, Sergiy Shelyag
Artificial neural networks (ANNs) are powerful tools capable of approximating any arbitrary mathematical function, but their interpretability remains limited, rendering them as bla…
cs.LG2024
Extremization to Fine Tune Physics Informed Neural Networks for Solving Boundary Value Problems
Abhiram Anand Thiruthummal, Sergiy Shelyag, Eun-jin Kim
We propose a novel method for fast and accurate training of physics-informed neural networks (PINNs) to find solutions to boundary value problems (BVPs) and initial boundary value…