no code implementations • 27 May 2024 • Ouail Kitouni, Niklas Nolte, Víctor Samuel Pérez-Díaz, Sokratis Trifinopoulos, Mike Williams
Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions.
no code implementations • 9 Jun 2023 • Ouail Kitouni, Niklas Nolte, Sokratis Trifinopoulos, Subhash Kantamneni, Mike Williams
We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning model that predicts various nuclear observables, including binding and decay energies, and nuclear charge radii.