Search for: All records

Creators/Authors contains: "Rolnick, D."

« Prev Next »

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

Cohan, S. ; Kim, N. H. ; Rolnick, D. ; van de Panne, M. ( December 2022 , NeurIPS)
Deep ReLU networks preserve expected length

Hanin, B. ; Jeong, R. ; Rolnick, D. ( May 2022 , ICLR)
Deep ReLU Networks Preserve Expected Length

Hanin, B ; Jeong, R ; Rolnick, D ( January 2022 , Advances in neural information processing systems)

Full Text Available
ClimART: A benchmark dataset for emulating atmospheric radiative transfer in weather and climate models

Cachay, S. R. ; Ramesh, V. ; Cole, J. N. ; Barker, H. ; Rolnick, D. ( December 2021 , NeurIPS)
DC3: A learning method for optimization with hard constraints

Donti, P. L. ; Rolnick, D. ; Kolter, J. Z. ( May 2021 , ICLR)
Deep ReLU Networks Preserve Expected Length

Hanin, B ; Jeong, R. ; Rolnick, D ( January 2021 , Advances in neural information processing systems)

Full Text Available
Reverse-engineering deep ReLU networks

Rolnick, D. ; Kording, K. ( July 2020 , ICML)
Deep ReLU networks have surprisingly few activation patterns

Hanin, B. ; Rolnick, D. ( December 2019 , NeurIPS)
Complexity of linear regions in deep networks

Hanin, B. ; Rolnick, D. ( July 2019 , ICML)
Experience replay for continual learning

Rolnick, D. ; Ahuja, A. ; Schwarz, J. ; Lillicrap, T. ; Wayne, G. ( December 2019 , NeurIPS)

« Prev Next »