Matrix momentum for practical natural gradient learning

This publication has 11 references indexed in Scilit:

• Superefficiency in blind source separation
  IEEE Transactions on Signal Processing, 1999
• Natural Gradient Descent for On-Line Learning
  Physical Review Letters, 1998
• Analysis of on-line training with optimal learning rates
  Physical Review E, 1998
• Natural Gradient Works Efficiently in Learning
  Neural Computation, 1998
• Globally Optimal Parameters for On-Line Learning in Multilayer Neural Networks
  Physical Review Letters, 1997
• On-line learning in soft committee machines
  Physical Review E, 1995
• Exact Solution for On-Line Learning in Multilayer Neural Networks
  Physical Review Letters, 1995
• Stochastic dynamics of learning with momentum in neural networks
  Journal of Physics A: General Physics, 1994
• Statistical Theory of Learning Curves under Entropic Loss Criterion
  Neural Computation, 1993
• Approximation by superpositions of a sigmoidal function
  Mathematics of Control, Signals, and Systems, 1989