referees correctly identified the main contributions of this work, namely: 1) a physically-inspired RNN generalising
–Neural Information Processing Systems
We are grateful to the anonymous referees for their valuable comments and suggestions. A smoother introduction of equation (2) would be nice. To retain the PGD interpretation of the network, one can use truncated ReLus as activation functions. I believe that the experimental results section could have been larger, with more results to support the claims. The ninth page will comment further on the experimental results.
Neural Information Processing Systems
Nov-19-2025, 10:13:57 GMT
- Technology: