An Evaluation of Fisher Approximations Beyond Kronecker Factorization
暂无分享,去创建一个
Pascal Vincent | César Laurent | Nicolas Ballas | Thomas George | Xavier Bouthillier | Pascal Vincent | Nicolas Ballas | Xavier Bouthillier | César Laurent | Thomas George
[1] Luca Antiga,et al. Automatic differentiation in PyTorch , 2017 .
[2] Roger B. Grosse,et al. Distributed Second-Order Optimization using Kronecker-Factored Approximations , 2016, ICLR.
[3] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .
[4] Nicol N. Schraudolph. Fast Curvature Matrix-Vector Products , 2001, ICANN.
[5] Tom Heskes,et al. On Natural Learning and Pruning in Multilayered Perceptrons , 2000, Neural Computation.
[6] Razvan Pascanu,et al. Natural Neural Networks , 2015, NIPS.
[7] Sergey Ioffe,et al. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.
[8] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[9] Jian Sun,et al. Identity Mappings in Deep Residual Networks , 2016, ECCV.
[10] Shun-ichi Amari,et al. Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.
[11] A. Conv. A Kronecker-factored approximate Fisher matrix for convolution layers , 2016 .
[12] Yann Dauphin,et al. Convolutional Sequence to Sequence Learning , 2017, ICML.
[13] Andrew Zisserman,et al. Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.