Avoiding pathologies in very deep networks

24 February 2014

Papers citing "Avoiding pathologies in very deep networks"

11 / 11 papers shown

Title
Adaptive RKHS Fourier Features for Compositional Gaussian Process Models Xinxing Shi Thomas Baldwin-McDonald Mauricio A. Álvarez 94 0 0 01 Jul 2024
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks Andrew M. Saxe James L. McClelland Surya Ganguli ODL 128 1,830 0 20 Dec 2013
High-Dimensional Probability Estimation with Deep Density Models Oren Rippel Ryan P. Adams 111 124 0 20 Feb 2013
Structure Discovery in Nonparametric Regression through Compositional Kernel Search David Duvenaud J. Lloyd Roger C. Grosse J. Tenenbaum Zoubin Ghahramani 65 509 0 20 Feb 2013
Gaussian Process Regression with Heteroscedastic or Non-Gaussian Residuals Chunyi Wang Radford M. Neal 71 52 0 26 Dec 2012
On the difficulty of training Recurrent Neural Networks Razvan Pascanu Tomas Mikolov Yoshua Bengio ODL 134 5,318 0 21 Nov 2012
Deep Gaussian Processes Andreas C. Damianou Neil D. Lawrence GP BDL 75 1,178 0 02 Nov 2012
Improving neural networks by preventing co-adaptation of feature detectors Geoffrey E. Hinton Nitish Srivastava A. Krizhevsky Ilya Sutskever Ruslan Salakhutdinov VLM 385 7,650 0 03 Jul 2012
Additive Gaussian Processes David Duvenaud H. Nickisch C. Rasmussen GP 87 329 0 19 Dec 2011
Gaussian Process Regression Networks A. Wilson David A. Knowles Zoubin Ghahramani GP BDL 122 192 0 19 Oct 2011
Learning the Structure of Deep Sparse Graphical Models Ryan P. Adams Hanna M. Wallach Zoubin Ghahramani 182 87 0 31 Dec 2009