no code implementations • 1 Jan 2021 • Daniel Lengyel, Nicholas Jennings, Panos Parpas, Nicholas Kantas
The intuitive connection to robustness and convincing empirical evidence have made the flatness of the loss surface an attractive measure of generalizability for neural networks.
1 code implementation • 14 Nov 2020 • Daniel Lengyel, Janith Petangoda, Isak Falk, Kate Highnam, Michalis Lazarou, Arinbjörn Kolbeinsson, Marc Peter Deisenroth, Nicholas R. Jennings
We propose an efficient algorithm to visualise symmetries in neural networks.