Obserwuj
Jascha Sohl-Dickstein
Jascha Sohl-Dickstein
Google Brain
Zweryfikowany adres z google.com - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Deep unsupervised learning using nonequilibrium thermodynamics
J Sohl-Dickstein, EA Weiss, N Maheswaranathan, S Ganguli
International Conference on Machine Learning, 2015
37312015
Unrolled generative adversarial networks
L Metz, B Poole, D Pfau, J Sohl-Dickstein
International Conference on Learning Representations, 2017
36972017
Density estimation using Real NVP
L Dinh, J Sohl-Dickstein, S Bengio
International Conference on Learning Representations, 2017
35342017
Score-Based Generative Modeling through Stochastic Differential Equations
Y Song, J Sohl-Dickstein, DP Kingma, A Kumar, S Ermon, B Poole
ICLR, oral, outstanding paper award, 2021
30062021
Deep knowledge tracing
C Piech, J Spencer, J Huang, S Ganguli, M Sahami, L Guibas, ...
Neural Information Processing Systems, 2015
13302015
Deep neural networks as gaussian processes
J Lee, Y Bahri, R Novak, SS Schoenholz, J Pennington, J Sohl-Dickstein
International Conference on Learning Representations, 2017
11442017
Wide neural networks of any depth evolve as linear models under gradient descent
J Lee, L Xiao, SS Schoenholz, Y Bahri, R Novak, J Sohl-Dickstein, ...
Neural Information Processing Systems, 2019
9792019
On the expressive power of deep neural networks
M Raghu, B Poole, J Kleinberg, S Ganguli, J Sohl-Dickstein
International Conference on Machine Learning, 2017
8772017
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ...
TMLR, 2022
6942022
Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability
M Raghu, J Gilmer, J Yosinski, J Sohl-Dickstein
Neural Information Processing Systems, 2017
6442017
Exponential expressivity in deep neural networks through transient chaos
B Poole, S Lahiri, M Raghu, J Sohl-Dickstein, S Ganguli
Neural Information Processing Systems, 3360-3368, 2016
6012016
Stratigraphy and sedimentology of a dry to wet eolian depositional system, Burns formation, Meridiani Planum, Mars
JP Grotzinger, RE Arvidson, JF Bell Iii, W Calvin, BC Clark, DA Fike, ...
Earth and Planetary Science Letters 240 (1), 11-72, 2005
5872005
Sensitivity and generalization in neural networks: an empirical study
R Novak, Y Bahri, DA Abolafia, J Pennington, J Sohl-Dickstein
International Conference on Learning Representations, 2018
4592018
Measuring the effects of data parallelism on neural network training
CJ Shallue, J Lee, J Antognini, J Sohl-Dickstein, R Frostig, GE Dahl
Journal of Machine Learning Research, 2019
4082019
Deep information propagation
SS Schoenholz, J Gilmer, S Ganguli, J Sohl-Dickstein
International Conference on Learning Representations, 2017
3882017
Adversarial examples that fool both computer vision and time-limited humans
GF Elsayed, S Shankar, B Cheung, N Papernot, A Kurakin, I Goodfellow, ...
Neural Information Processing Systems, 2018
3612018
Mars exploration rover Athena panoramic camera (Pancam) investigation
JF Bell III, SW Squyres, KE Herkenhoff, JN Maki, HM Arneson, D Brown, ...
Journal of Geophysical Research: Planets 108 (E12), 2003
3502003
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
L Xiao, Y Bahri, J Sohl-Dickstein, SS Schoenholz, J Pennington
International Conference on Machine Learning, 2018
3452018
Rebar: Low-variance, unbiased gradient estimates for discrete latent variable models
G Tucker, A Mnih, CJ Maddison, J Lawson, J Sohl-Dickstein
Neural Information Processing Systems, oral presentation, 2627-2636, 2017
3352017
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
R Novak, L Xiao, J Lee, Y Bahri, G Yang, D Abolafia, J Pennington, ...
International Conference on Learning Representations, 2019
3332019
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20