Sledovať
Surya Ganguli
Surya Ganguli
Associate Professor, Stanford University
Overená e-mailová adresa na: stanford.edu - Domovská stránka
Názov
Citované v
Citované v
Rok
Deep unsupervised learning using nonequilibrium thermodynamics
J Sohl-Dickstein, E Weiss, N Maheswaranathan, S Ganguli
International conference on machine learning, 2256-2265, 2015
70942015
Continual learning through synaptic intelligence
F Zenke, B Poole, S Ganguli
International conference on machine learning, 3987-3995, 2017
31052017
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
22932013
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
YN Dauphin, R Pascanu, C Gulcehre, K Cho, S Ganguli, Y Bengio
Advances in neural information processing systems 27, 2014
19002014
Deep knowledge tracing
C Piech, J Bassen, J Huang, S Ganguli, M Sahami, LJ Guibas, ...
Advances in neural information processing systems 28, 2015
17002015
Holistic evaluation of language models
P Liang, R Bommasani, T Lee, D Tsipras, D Soylu, M Yasunaga, Y Zhang, ...
arXiv preprint arXiv:2211.09110, 2022
12172022
On the expressive power of deep neural networks
M Raghu, B Poole, J Kleinberg, S Ganguli, J Sohl-Dickstein
international conference on machine learning, 2847-2854, 2017
10142017
A deep learning framework for neuroscience
BA Richards, TP Lillicrap, P Beaudoin, Y Bengio, R Bogacz, ...
Nature neuroscience 22 (11), 1761-1770, 2019
9942019
Pruning neural networks without any data by iteratively conserving synaptic flow
H Tanaka, D Kunin, DL Yamins, S Ganguli
Advances in neural information processing systems 33, 6377-6389, 2020
7532020
Superspike: Supervised learning in multilayer spiking neural networks
F Zenke, S Ganguli
Neural computation 30 (6), 1514-1541, 2018
7102018
Exponential expressivity in deep neural networks through transient chaos
B Poole, S Lahiri, M Raghu, J Sohl-Dickstein, S Ganguli
Advances in neural information processing systems, 3360-3368, 2016
6932016
Cortical layer–specific critical dynamics triggering perception
JH Marshel, YS Kim, TA Machado, S Quirin, B Benson, J Kadmon, C Raja, ...
Science 365 (6453), eaaw5202, 2019
6122019
Deep learning on a data diet: Finding important examples early in training
M Paul, S Ganguli, GK Dziugaite
Advances in neural information processing systems 34, 20596-20607, 2021
4582021
Deep information propagation
SS Schoenholz, J Gilmer, S Ganguli, J Sohl-Dickstein
arXiv preprint arXiv:1611.01232, 2016
4442016
Beyond neural scaling laws: beating power law scaling via data pruning
B Sorscher, R Geirhos, S Shekhar, S Ganguli, A Morcos
Advances in Neural Information Processing Systems 35, 19523-19536, 2022
4082022
On simplicity and complexity in the brave new world of large-scale neuroscience
P Gao, S Ganguli
Current opinion in neurobiology 32, 148-155, 2015
4032015
Memory traces in dynamical systems
S Ganguli, D Huh, H Sompolinsky
Proceedings of the national academy of sciences 105 (48), 18970-18975, 2008
3892008
Understanding self-supervised learning dynamics without contrastive pairs
Y Tian, X Chen, S Ganguli
International Conference on Machine Learning, 10268-10278, 2021
3372021
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
3332019
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
J Pennington, S Schoenholz, S Ganguli
Advances in neural information processing systems 30, 2017
3252017
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–20