Logo image
Scaling properties in neural network learning
Conference proceeding

Scaling properties in neural network learning

M.C Schiminsky and B Onaral
Proceedings of the 1991 IEEE Seventeenth Annual Northeast Bioengineering Conference, pp 49-50
1991

Abstract

Biomedical engineering Biomedical measurements Design engineering Geometry Intelligent networks Microscopy Neural networks Power engineering and energy Psychology Systems engineering and theory
Working definitions of learning and learners are examined from the scaling point of view. A back-error propagation neural network was trained to plot sin (x) given an input x (- pi >or= x >or= pi ). The parameters for the simulation are the following: input-output (pattern) pairs=200; input units=1; hidden units=20; output units=1; learning rates=0.1; momentum term constant=0.2; weights and thresholds set to random values between (-1, 1); number of trials where input samples were randomly selected=8585. The performance curve consists of the cumulated number of errors less than 0.1 in absolute value vs trial number. It is noted that the scaling exponent ranges from a value of 0.34 in the lower decade (10-100) to 0.66 in the upper decade (1000-10000), reflecting the heterogeneities in scaling along the training process.< >

Metrics

9 Record Views

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Engineering, Biomedical
Medical Laboratory Technology
Logo image