Johnson Distributions for Fitting Weighted Sums of Sigmoided Neuron Outputs
Abstract
In this paper, it is shown that a continuum of distributions best characterizes the hidden layer outputs of a multilayer perceptron when trained as a 0-1 classifier and tested with a range of signal-to-noise ratio (SNR) input distributions. A four parameter system of transformed normal distributions, known as the Johnson system of distributions, is utilized to illustrate the shape of output distributions as a function of input SNR levels. Neural networks, Active signal processing.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 11, 1993
- Accession Number
- ADA273259
Entities
People
- J. T. Durham
- W. C. Torrez
Organizations
- Naval Command, Control and Ocean Surveillance Center