| Deep unsupervised learning using nonequilibrium thermodynamics J Sohl-Dickstein, E Weiss, N Maheswaranathan, S Ganguli International conference on machine learning, 2256-2265, 2015 | 5420 | 2015 |
| Learned optimizers that scale and generalize O Wichrowska, N Maheswaranathan, MW Hoffman, SG Colmenarejo, ... International conference on machine learning, 3751-3760, 2017 | 317 | 2017 |
| Deep learning models of the retinal response to natural scenes L McIntosh, N Maheswaranathan, A Nayebi, S Ganguli, S Baccus Advances in neural information processing systems 29, 2016 | 296 | 2016 |
| A multiplexed, heterogeneous, and adaptive code for navigation in medial entorhinal cortex K Hardcastle, N Maheswaranathan, S Ganguli, LM Giocomo Neuron 94 (2), 375-387. e7, 2017 | 280 | 2017 |
| Social control of hypothalamus-mediated male aggression T Yang, CF Yang, MD Chizari, N Maheswaranathan, KJ Burke, M Borius, ... Neuron 95 (4), 955-970. e4, 2017 | 158 | 2017 |
| Understanding and correcting pathologies in the training of learned optimizers L Metz, N Maheswaranathan, J Nixon, D Freeman, J Sohl-Dickstein International Conference on Machine Learning, 4556-4565, 2019 | 148 | 2019 |
| Universality and individuality in neural dynamics across large populations of recurrent networks N Maheswaranathan, A Williams, M Golub, S Ganguli, D Sussillo Advances in neural information processing systems 32, 2019 | 142 | 2019 |
| Meta-learning update rules for unsupervised representation learning L Metz, N Maheswaranathan, B Cheung, J Sohl-Dickstein arXiv preprint arXiv:1804.00222, 2018 | 140 | 2018 |
| Guided evolutionary strategies: Augmenting random search with surrogate gradients N Maheswaranathan, L Metz, G Tucker, D Choi, J Sohl-Dickstein International Conference on Machine Learning, 4264-4273, 2019 | 121* | 2019 |
| Discovering precise temporal patterns in large-scale neural recordings through robust and interpretable time warping AH Williams, B Poole, N Maheswaranathan, AK Dhawale, T Fisher, ... Neuron 105 (2), 246-259. e8, 2020 | 95 | 2020 |
| Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics N Maheswaranathan, A Williams, M Golub, S Ganguli, D Sussillo Advances in neural information processing systems 32, 2019 | 89 | 2019 |
| From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction H Tanaka, A Nayebi, N Maheswaranathan, L McIntosh, S Baccus, ... Advances in neural information processing systems 32, 2019 | 75 | 2019 |
| Inferring hidden structure in multilayered neural circuits N Maheswaranathan, DB Kastner, SA Baccus, S Ganguli PLoS computational biology 14 (8), e1006291, 2018 | 73 | 2018 |
| Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves L Metz, N Maheswaranathan, CD Freeman, B Poole, J Sohl-Dickstein arXiv preprint arXiv:2009.11243, 2020 | 57 | 2020 |
| Learning unsupervised learning rules L Metz, N Maheswaranathan, B Cheung, J Sohl-Dickstein International Conference on Learning Representations, 2019 | 48 | 2019 |
| Deep learning models reveal internal structure and diverse computations in the retina under natural scenes N Maheswaranathan, LT McIntosh, DB Kastner, JB Melander, L Brezovec, ... BioRxiv, 340943, 2018 | 41 | 2018 |
| Using a thousand optimization tasks to learn hyperparameter search strategies L Metz, N Maheswaranathan, R Sun, CD Freeman, B Poole, ... arXiv preprint arXiv:2002.11887, 2020 | 38 | 2020 |
| How recurrent networks implement contextual processing in sentiment analysis N Maheswaranathan, D Sussillo arXiv preprint arXiv:2004.08013, 2020 | 28 | 2020 |
| Emergent bursting and synchrony in computer simulations of neuronal cultures N Maheswaranathan, S Ferrari, AMJ VanDongen, CS Henriquez Frontiers in computational neuroscience 6, 15, 2012 | 28 | 2012 |
| Practical tradeoffs between memory, compute, and performance in learned optimizers L Metz, CD Freeman, J Harrison, N Maheswaranathan, J Sohl-Dickstein Conference on Lifelong Learning Agents, 142-164, 2022 | 27 | 2022 |
Jascha Sohl-DicksteinAnthropicVerified email at anthropic.com
