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.
Farag, I., & Ibrahim, F. (1995). NEURAL NETWORK IMPLEMENTATION OF BINARY TREES. International Conference on Aerospace Sciences and Aviation Technology, 6(ASAT CONFERENCE 2 — 4 May 1995, CAIRO), 131-139. doi: 10.21608/asat.1995.25572
MLA
Ismail A. Farag; Fawzy Ibrahim. "NEURAL NETWORK IMPLEMENTATION OF BINARY TREES". International Conference on Aerospace Sciences and Aviation Technology, 6, ASAT CONFERENCE 2 — 4 May 1995, CAIRO, 1995, 131-139. doi: 10.21608/asat.1995.25572
HARVARD
Farag, I., Ibrahim, F. (1995). 'NEURAL NETWORK IMPLEMENTATION OF BINARY TREES', International Conference on Aerospace Sciences and Aviation Technology, 6(ASAT CONFERENCE 2 — 4 May 1995, CAIRO), pp. 131-139. doi: 10.21608/asat.1995.25572
VANCOUVER
Farag, I., Ibrahim, F. NEURAL NETWORK IMPLEMENTATION OF BINARY TREES. International Conference on Aerospace Sciences and Aviation Technology, 1995; 6(ASAT CONFERENCE 2 — 4 May 1995, CAIRO): 131-139. doi: 10.21608/asat.1995.25572
)
View on SCiNiTO