Title :
Generalization in multi-layer networks of Sigma-pi units
Author :
Penny, W.D. ; Stonham, T.J.
Author_Institution :
Dept. of Electr. Eng. & Electron., Brunel Univ., Uxbridge, UK
fDate :
3/1/1995 12:00:00 AM
Abstract :
This paper investigates a method for predicting the generalization error that a multi-layer network of Sigma-pi units will, on average, exhibit. Theoretical values are compared with those obtained by the computer simulation of small networks learning parity and contiguity functions
Keywords :
digital simulation; generalisation (artificial intelligence); multilayer perceptrons; neural nets; Sigma-pi units; computer simulation; contiguity functions; generalization error; multilayer networks; small networks learning parity; Boolean functions; Computer errors; Computer simulation; Intelligent networks; Logic circuits; Multi-layer neural network; Neural network hardware; Neural networks; Probabilistic logic; Random access memory;
Journal_Title :
Neural Networks, IEEE Transactions on
