Conference proceeding
Scaling properties in neural network learning
Proceedings of the 1991 IEEE Seventeenth Annual Northeast Bioengineering Conference, pp 49-50
1991
Abstract
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
- Title
- Scaling properties in neural network learning
- Creators
- M.C Schiminsky - Drexel UniversityB Onaral - Drexel University
- Publication Details
- Proceedings of the 1991 IEEE Seventeenth Annual Northeast Bioengineering Conference, pp 49-50
- Conference
- 1991 IEEE Seventeenth Annual Northeast Bioengineering Conference, 17th
- Publisher
- IEEE
- Number of pages
- 1
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems
- Web of Science ID
- WOS:A1991BT54H00022
- Other Identifier
- 991019182763804721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Engineering, Biomedical
- Medical Laboratory Technology