Back to Results
First PageMeta Content
Estimation theory / Neural networks / Matrices / Computational neuroscience / Differential calculus / Fisher information / Maximum likelihood / Gradient / Linear map / Mathematics / Mathematical analysis / Calculus


Optimizing Neural Networks with Kronecker-factored Approximate Curvature James Martens Roger Grosse Department of Computer Science, University of Toronto
Add to Reading List

Document Date: 2015-06-03 15:15:50

Open Document

File Size: 846,13 KB

Share Result on Facebook

City

Berlin / TORONTO / Lille / /

Company

Neural Information Processing Systems / Neural Networks / MIT Press / no- Optimizing Neural Networks / GPU / Google / ma- Optimizing Neural Networks / Oxford University Press / SIAM Journal / Optimizing Neural Networks / Intel / /

Country

France / /

Facility

University of Toronto Abstract We / Carnegie Mellon University / University of Toronto / /

IndustryTerm

online estimates / optimization algorithm / default network / large networks / matrix-vector products / Information-geometric optimization algorithms / natural gradient algorithm / curvature matrix-vector products / natural gradient learning algorithms / stochastic approximation algorithms / bank / recurrent networks / computing / online estimation / /

Organization

Connectionist Models Summer School / MIT / Approximate Curvature James Martens Roger Grosse Department of Computer Science / NSERC / Department of Computer Science / University of Toronto Abstract We / Carnegie Mellon University / Pittsburgh / Oxford University / University of Toronto / /

Person

Ludovic Arnold / George Dahl / Sanjeev Khudanpur / Py / Geoffrey E. Hinton / Xavier Glorot / Silvia Scarpetta / David Saad / Harri Valpola / Alex Krizhevsky / Jorge Nocedal / Matthew D. Zeiler / Tom Heskes / Cleve B. Moler / Christopher M. Bishop / Stephen J. Wright / Nikolaus Hansen / Tommi Vatanen / Xiaohui Zhang / Anne Auger / Yann Ollivier / Roger Grosse / Hermann Ney / Ilya Sutskever / Yurii Nesterov / Judith D. Gardiner / Tapani Raiko / Ruslan Salakhutdinov / Alexander Richard / James J. Amato / Daniel Povey / Magnus Rattray / James Martens / Sue Becker / Ralf Schl¨uter / Nicol N. Schraudolph / Mark W. Schmidt / Sixin Zhang / Shun-Ichi Amari / Ryan Kiros / Eric Chu / Nitish Srivastava / Michael P. Friedlander / Alan J. Laub / Nicolas Le Roux / Yoshua Bengio / Simon Wiesler / Yann LeCun / John E. Moody / Tom Schaul / Razvan Pascanu / /

Position

approximate Fisher / inverse Fisher / General / author / block-wise Kronecker-factored Fisher / model / Bishop / Fisher information matrix / feed-forward / various Fisher / Fisher / associated Fisher information matrix / /

Product

Fisher / Kronecker / /

ProgrammingLanguage

MATLAB / K / E / /

ProvinceOrState

Pennsylvania / /

PublishedMedium

Machine Learning / Journal of Physics A / Lecture Notes in Computer Science / /

RadioStation

KSD / /

Technology

Adaptive natural gradient learning algorithms / Levenberg-Marquardt algorithm / Machine Learning / online natural gradient algorithm / optimization algorithm / Information-geometric optimization algorithms / neural network / artificial intelligence / stochastic approximation algorithms / /

SocialTag