论文信息 - Multi-Dimensional Density Shaping by Sigmoidal Networks

Multi-Dimensional Density Shaping by Sigmoidal Networks

An estimate of the probability density function of a random vector is obtained by maximizing the output entropy of a feed-forward network of sigmoidal units with respect to the input weights. particularly suitable for “real time” prediction. A triangular connectivity between the neurons and the input, which is naturally suggested by the statistical setting, reduces the number of parameters.

Y. Baram | Z. Roth | Y. Baram | Z. Roth

[1] W. Dixon,et al. Introduction to Mathematical Statistics. , 1964 .

[2] John G. Proakis,et al. Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[3] Halbert White,et al. Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[4] Peter Seitz,et al. Minimum class entropy: A maximum information approach to layered networks , 1989, Neural Networks.

[5] Ralph Linsker,et al. How to Generate Ordered Maps by Maximizing the Mutual Information between Input and Output Signals , 1989, Neural Computation.

[6] Allen Gersho,et al. The Boltzmann Perceptron Network: A soft classifier , 1990, Neural Networks.

[7] Hans G. C. Tråvén,et al. A neural network approach to statistical pattern classification by 'semiparametric' estimation of probability density functions , 1991, IEEE Trans. Neural Networks.

[8] Richard Lippmann,et al. Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.

[9] Uwe Hartmann,et al. Mapping neural network derived from the parzen window estimator , 1992, Neural Networks.

[10] Roberto Battiti,et al. Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[11] Terrence J. Sejnowski,et al. An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.