Noether Networks: Meta-Learning Useful Conserved Quantities — mentioned by raptortech

Fri, 01 Mar 2024 18:27:09 GMT

See also "Noether Networks: Meta-Learning Useful Conserved Quantities" https://arxiv.org/abs/2112.03321 from 2021. Abstract: Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on…

Paper and discussion history. A mention is not an endorsement.

Noether Networks: Meta-Learning Useful Conserved Quantities · HackerPapers discussions

Noether Networks: Meta-Learning Useful Conserved Quantities — mentioned by raptortech