Rochester Institute of Technology
Monte Carlo comparison of back-propagation, conjugate-gradient, and finite-difference training algorithms for multilayer perceptrons
Abstract
dc:description.abstractMonte Carlo Simulation is used to compare the performance of the Back-Propagation, Conjugate-Gradient, and Finite-Difference algorithms when training simple Multilayer Perceptron networks to solve pattern recognition and bit counting problems. Twelve individual simulations will be run for each training algorithm-test problem combination, resulting in an overall total of 72 simulations. The random elements in each Monte Carlo simulation are to be the individual synaptic weights between layers, which will be uniformly distributed. Two other factors, the size of the hidden layer and the exponent of the error function, will also be tested within the simulation plan outlined above.
Degree
thesis:*- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- School of Mathematical Sciences (COS)
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Wehry, Stephen
- Contributors dc:contributor
-
- Engel, Alejandro
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/223