NEURAL NETWORK IMPLEMENTATION OF BINARY TREES | ||||
International Conference on Aerospace Sciences and Aviation Technology | ||||
Article 11, Volume 6, ASAT CONFERENCE 2 — 4 May 1995, CAIRO, May 1995, Page 131-139 PDF (2.4 MB) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/asat.1995.25572 | ||||
View on SCiNiTO | ||||
Authors | ||||
Ismail A. Farag; Fawzy Ibrahim | ||||
Dr., Department of Specialized Electrical Engineering, Military Technical College Cairo, Egypt. | ||||
Abstract | ||||
Multiple layer artificial neural network (ANN) structure is capable of implementing arbitrary input-output mappings. Similarly, hierarchical classifiers, more commonly known as decision trees, possess the capabilities of generating arbitrarily complex decision boundaries in an n-dimensional space. Given a decision tree, it is possible to restructure it as a multilayered neural network. The objective of this paper is to show how this mapping of decision trees into multilayer neural network structure can be exploited for the systematic design of a class of layered neural networks, called entropy nets, that have far fewer connections. | ||||
Statistics Article View: 153 PDF Download: 247 |
||||