Functional expansion representations of artificial neural networks
- Author
- Gray, W. Steven
- Published
- Sep 1, 1992.
- Physical Description
- 1 electronic document
Online Version
- hdl.handle.net , Connect to this object online.
- Restrictions on Access
- Unclassified, Unlimited, Publicly available.
Free-to-read Unrestricted online access - Summary
- In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.
- Other Subject(s)
- Collection
- NASA Technical Reports Server (NTRS) Collection.
- Note
- Document ID: 19930007583.
Accession ID: 93N16772.
Hampton Univ., NASA(American Society for Engineering Education (ASEE) Summer Faculty Fellowship Program 1992 p 121-123 (SEE N93-16760 05-80); Hampton Univ., NASA(. - Terms of Use and Reproduction
- No Copyright.
View MARC record | catkey: 15672942