| A unified framework of online learning algorithms for training recurrent neural networks O Marschall, K Cho, C Savin Journal of machine learning research 21 (135), 1-34, 2020 | 79 | 2020 |
| Non-archimedean connected Julia sets with branching D Bajpai, RL Benedetto, R Chen, E Kim, O Marschall, D Onul, Y Xiao Ergodic Theory and Dynamical Systems 37 (1), 59-78, 2017 | 6 | 2017 |
| Using local plasticity rules to train recurrent neural networks O Marschall, K Cho, C Savin arXiv preprint arXiv:1905.12100, 2019 | 5 | 2019 |
| Probing learning through the lens of changes in circuit dynamics O Marschall, C Savin bioRxiv, 2023.09. 13.557585, 2023 | 4 | 2023 |
| Evaluating biological plausibility of learning algorithms the lazy way O Marschall, K Cho, C Savin Real Neurons {\&} Hidden Units: Future directions at the intersection of …, 2019 | 4 | 2019 |
| Connectivity structure and dynamics of nonlinear recurrent neural networks DG Clark, O Marschall, A van Meegen, A Litwin-Kumar arXiv preprint arXiv:2409.01969, 2024 | | 2024 |
| Learning Dynamics and the Dynamics of Learning OE Marschall New York University, 2022 | | 2022 |
| Computing the entropy of certain p-adic dynamical systems D Bajpai, R Chen, E Kim, O Marschall, D Onul, Y Xiao | | |
