The Loss Surface of Multilayer Networks

[1]  Surya Ganguli,et al.  Identifying and attacking the saddle point problem in high-dimensional non-convex optimization , 2014, NIPS.

[2]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[3]  Surya Ganguli,et al.  Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , 2013, ICLR.

[4]  Misha Denil,et al.  Predicting Parameters in Deep Learning , 2014 .

[5]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[6]  Antonio Auffinger,et al.  Complexity of random smooth functions on the high-dimensional sphere , 2011, 1110.5872.

[7]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[8]  Antonio Auffinger,et al.  Random Matrices and Complexity of Spin Glasses , 2010, 1003.1129.

[9]  Yan V Fyodorov,et al.  Replica Symmetry Breaking Condition Exposed by Random Matrix Calculation of Landscape Complexity , 2007, cond-mat/0702601.

[10]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  Saad,et al.  Exact solution for on-line learning in multilayer neural networks. , 1995, Physical review letters.

[13]  V. Dotsenko.  An Introduction to the Theory of Spin Glasses and Neural Networks , 1995 .

[14]  Pierre Priouret,et al.  Adaptive Algorithms and Stochastic Approximations , 1990, Applications of Mathematics.

[15]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[16]  Sompolinsky,et al.  Spin-glass models of neural networks. , 1985, Physical review. A, General physics.