| Exact solutions to the nonlinear dynamics of learning in deep linear neural networks AM Saxe, JL McClelland, S Ganguli arXiv preprint arXiv:1312.6120, 2013 | 1157 | 2013 |
| Measuring invariances in deep networks I Goodfellow, H Lee, Q Le, A Saxe, A Ng Advances in neural information processing systems 22, 646-654, 2009 | 454 | 2009 |
| On random weights and unsupervised feature learning AM Saxe, PW Koh, Z Chen, M Bhand, B Suresh, AY Ng Icml, 2011 | 432 | 2011 |
| Qualitatively characterizing neural network optimization problems IJ Goodfellow, O Vinyals, AM Saxe arXiv preprint arXiv:1412.6544, 2014 | 330 | 2014 |
| On the information bottleneck theory of deep learning AM Saxe, Y Bansal, J Dapello, M Advani, A Kolchinsky, BD Tracey, ... Journal of Statistical Mechanics: Theory and Experiment 2019 (12), 124020, 2019 | 228 | 2019 |
| High-dimensional dynamics of generalization error in neural networks MS Advani, AM Saxe, H Sompolinsky Neural Networks 132, 428-446, 2020 | 208 | 2020 |
| A deep learning framework for neuroscience BA Richards, TP Lillicrap, P Beaudoin, Y Bengio, R Bogacz, ... Nature neuroscience 22 (11), 1761-1770, 2019 | 207 | 2019 |
| Acquisition of decision making criteria: reward rate ultimately beats accuracy F Balci, P Simen, R Niyogi, A Saxe, JA Hughes, P Holmes, JD Cohen Attention, Perception, & Psychophysics 73 (2), 640-657, 2011 | 155 | 2011 |
| Deterministic matrices matching the compressed sensing phase transitions of Gaussian random matrices H Monajemi, S Jafarpour, M Gavish, DL Donoho, ... Proceedings of the National Academy of Sciences 110 (4), 1181-1186, 2013 | 102 | 2013 |
| A mathematical theory of semantic development in deep neural networks AM Saxe, JL McClelland, S Ganguli Proceedings of the National Academy of Sciences 116 (23), 11537-11546, 2019 | 74 | 2019 |
| Learning hierarchical category structure in deep neural networks AM Saxe, JL McClelland, S Ganguli Proceedings of the 35th annual meeting of the Cognitive Science Society …, 0 | 64* | |
| Multitasking capability versus learning efficiency in neural network architectures S Musslick, A Saxe, K Özcimder, B Dey, G Henselman, JD Cohen Cognitive Science Society, 2017 | 58 | 2017 |
| Unsupervised learning models of primary cortical receptive fields and receptive field plasticity A Saxe, M Bhand, R Mudur, B Suresh, AY Ng Shawe-Taylor, J.; Zemel, R.; Bartlett, P, 2011 | 56 | 2011 |
| Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup S Goldt, MS Advani, AM Saxe, F Krzakala, L Zdeborová arXiv preprint arXiv:1906.08632, 2019 | 46 | 2019 |
| Active long term memory networks T Furlanello, J Zhao, AM Saxe, L Itti, BS Tjan arXiv preprint arXiv:1606.02355, 2016 | 37 | 2016 |
| Energy–entropy competition and the effectiveness of stochastic gradient descent in machine learning Y Zhang, AM Saxe, MS Advani, AA Lee Molecular Physics 116 (21-22), 3214-3223, 2018 | 33 | 2018 |
| Modeling cortical representational plasticity with unsupervised feature learning A Saxe, M Bhand, R Mudur, B Suresh, A Ng Poster presented at COSYNE, 24-27, 2011 | 33 | 2011 |
| DARPA Urban Challenge Princeton University Technical Paper AL Kornhauser, A Atreya, B Cattle, S Momen, B Collins, A Downey, ... Princeton University: Princeton, NJ, USA, 2007 | 25 | 2007 |
| If deep learning is the answer, what is the question? A Saxe, S Nelli, C Summerfield Nature Reviews Neuroscience, 1-13, 2020 | 24* | 2020 |
| Hierarchy through composition with multitask LMDPs AM Saxe, AC Earle, B Rosman International Conference on Machine Learning, 3017-3026, 2017 | 21 | 2017 |
Surya GanguliAssociate Professor, Stanford UniversityVerified email at stanford.edu
