Author of the publication

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

On the importance of initialization and momentum in deep learning.

I. Sutskever, J. Martens, G. Dahl, and G. Hinton. ICML (3), volume 28 of JMLR Workshop and Conference Proceedings, page 1139-1147. JMLR.org, (2013)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Kenneth E M George

Sascha Dahl

Kooperative Planung in Logistiknetzwerken: Entwicklung und Evaluation von UnterstützungskonzeptenS. Dahl. Uni Köln, (2009)

Karl Dahl

Ernst Dahl

Johann Dahl

Other publications of authors with the same name

Pre-training helps Bayesian optimization too.Z. Wang, G. Dahl, K. Swersky, C. Lee, Z. Mariet, Z. Nado, J. Gilmer, J. Snoek, and Z. Ghahramani. CoRR, (2022)A Loss Curvature Perspective on Training Instability in Deep Learning.J. Gilmer, B. Ghorbani, A. Garg, S. Kudugunta, B. Neyshabur, D. Cardoze, G. Dahl, Z. Nado, and O. Firat. CoRR, (2021)Parallel Architecture and Hyperparameter Search via Successive Halving and Classification.M. Kumar, G. Dahl, V. Vasudevan, and M. Norouzi. CoRR, (2018)Deep Belief Networks using discriminative features for phone recognition.A. rahman Mohamed, T. Sainath, G. Dahl, B. Ramabhadran, G. Hinton, and M. Picheny. ICASSP, page 5060-5063. IEEE, (2011)Large scale distributed neural network training through online distillationR. Anil, G. Pereyra, A. Passos, R. Ormandi, G. Dahl, and G. Hinton. (2018)cite arxiv:1804.03235.Deep Convolutional Neural Networks for Large-scale Speech Tasks.T. Sainath, B. Kingsbury, G. Saon, H. Soltau, A. rahman Mohamed, G. Dahl, and B. Ramabhadran. Neural Networks, (2015)Training Restricted Boltzmann Machines on Word Observations.G. Dahl, R. Adams, and H. Larochelle. ICML, icml.cc / Omnipress, (2012)What Will it Take to Fix Benchmarking in Natural Language Understanding?S. Bowman, and G. Dahl. NAACL-HLT, page 4843-4855. Association for Computational Linguistics, (2021)Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes.R. Adams, G. Dahl, and I. Murray. CoRR, (2014)Motivating the Rules of the Game for Adversarial Example Research.J. Gilmer, R. Adams, I. Goodfellow, D. Andersen, and G. Dahl. CoRR, (2018)

BibSonomy

Disambiguation of "Dahl, George E."

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

On the importance of initialization and momentum in deep learning.

Please choose a person to relate this publication to

Kenneth E M George

Sascha Dahl

Karl Dahl

Ernst Dahl

Johann Dahl

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Dahl, George E."

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML On the importance of initialization and momentum in deep learning.

Please choose a person to relate this publication to

Kenneth E M George

Sascha Dahl

Karl Dahl

Ernst Dahl

Johann Dahl

Other publications of authors with the same name

Disambiguation

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

On the importance of initialization and momentum in deep learning.