论文信息 - A New Margin-Based Criterion for Efficient Gradient Descent

A New Margin-Based Criterion for Efficient Gradient Descent

Keywords: learning Note: Published in ``ICASSP, 2004'' Reference EPFL-REPORT-82916 URL: http://publications.idiap.ch/downloads/reports/2003/rr03-16.pdf Record created on 2006-03-10, modified on 2017-05-10

Samy Bengio | Ronan Collobert

[1] William H. Press,et al. Numerical Recipes in Fortran 77: The Art of Scientific Computing 2nd Editionn - Volume 1 of Fortran Numerical Recipes , 1992 .

[2] Heekuck Oh,et al. Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[3] Geoffrey E. Hinton,et al. Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[4] Yann LeCun,et al. Second Order Properties of Error Surfaces , 1990, NIPS.

[5] R. Fletcher. Practical Methods of Optimization , 1988 .

[6] Nicol N. Schraudolph,et al. Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent , 2002, Neural Computation.

[7] Shun-ichi Amari,et al. Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[8] Vladimir Vapnik,et al. The Nature of Statistical Learning , 1995 .

[9] Decision Boundary Focused Neural Network Classifier , 2022 .

[10] Roberto Battiti,et al. First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[11] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[12] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.