Accession Number : ADA299479

Title :   Neural Networks for Interactive Image and Signal Exploitation.

Descriptive Note : Final rept. 30 Sep 92-29 May 95,

Corporate Author : DAVID SARNOFF RESEARCH CENTER PRINCETON NJ

Personal Author(s) : Pearson, John

PDF Url : ADA299479

Report Date : 29 MAY 1995

Pagination or Media Count : 166

Abstract : Efficient reliable neural network design methods based on sound principles were developed. The main effort was concentrated on exploring the nature of error surfaces attempting to answer the question of how many minima actually exists in any given design. To this end the following experimental approach was taken: Define a scaleable model problem with a known solution, Perform comprehensive, careful training experiments, Refine training solutions to highly accurate minima, Post process and count local minima, and Derive quantitative and qualitative measures that describe error surfaces. The Principal results show: How the number of minima varies as a function of the ration of training to network size, the probability that training from a random start converges to a minimum, and How the number of minima increase with network complexity.

Descriptors :   *IMAGE PROCESSING, *NEURAL NETS, EXPERIMENTAL DATA, SIZES(DIMENSIONS), INTERACTIONS, OPTICAL IMAGES, SURFACES, SOLUTIONS(GENERAL).

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE