NIPS Proceedingsβ

Shun-ichi Amari

19 Papers

  • Modeling Memory Transfer and Saving in Cerebellar Motor Learning (2005)
  • Unbiased Estimator of Shape Parameter for Spiking Irregularities under Changing Environments (2005)
  • Sparse Representation and Its Applications in Blind Source Separation (2003)
  • Critical Lines in Symmetry of Mixture Models and its Application to Component Splitting (2002)
  • The Effect of Singularities in a Learning Machine when the True Parameters Do Not Lie on such Singularities (2002)
  • Geometrical Singularities in the Neuromanifold of Multilayer Perceptrons (2001)
  • Information Geometrical Framework for Analyzing Belief Propagation Decoder (2001)
  • Information-Geometrical Significance of Sparsity in Gallager Codes (2001)
  • Information-Geometric Decomposition in Spike Analysis (2001)
  • Neural Implementation of Bayesian Inference in Population Codes (2001)
  • Population Decoding Based on an Unfaithful Model (1999)
  • Semiparametric Approach to Multichannel Blind Deconvolution of Nonminimum Phase Systems (1999)
  • Convergence of the Wake-Sleep Algorithm (1998)
  • The Efficiency and the Robustness of Natural Gradient Descent Learning Rule (1997)
  • Adaptive On-line Learning in Changing Environments (1996)
  • Neural Learning in Structured Parameter Spaces - Natural Riemannian Gradient (1996)
  • A New Learning Algorithm for Blind Signal Separation (1995)
  • Statistical Theory of Overtraining - Is Cross-Validation Asymptotically Effective? (1995)
  • Learning Curves, Model Selection and Complexity of Neural Networks (1992)