Title :
A geometrical representation of McCulloch-Pitts neural model and its applications
Author :
Zhang, Ling ; Zhang, Bo
Author_Institution :
Artificial Intelligence Inst., Anhui Univ., Hefei, China
fDate :
7/1/1999 12:00:00 AM
Abstract :
In this paper, a geometrical representation of McCulloch-Pitts neural model (1943) is presented, From the representation, a clear visual picture and interpretation of the model can be seen. Two interesting applications based on the interpretation are discussed. They are 1) a new design principle of feedforward neural networks and 2) a new proof of mapping abilities of three-layer feedforward neural networks
Keywords :
feedforward neural nets; geometry; multilayer perceptrons; McCulloch-Pitts neural model; feedforward neural network design; geometrical representation; mapping abilities; three-layer feedforward neural networks; Artificial intelligence; Artificial neural networks; Computer science; Convergence; Feedforward neural networks; Intelligent systems; Mathematics; Neural networks; Neurons; Solid modeling;
Journal_Title :
Neural Networks, IEEE Transactions on
