Title :
Analysis and study of perceptron to solve XOR problem
Author :
Yanling, Zhao ; Bimin, Deng ; Zhanrong, Wang
Author_Institution :
Southwest Jiaotong Univ., Chengdu, China
Abstract :
This paper tries to explain the network structures and methods of single-layer perceptron and multi-layer perceptron. It also analyses the linear division and un-division problems in logical operation performed by single-layer perceptron. XOR is linear un-division operation, which cannot be treated by single-layer perceptron. With the analysis, several solutions are proposed in the paper to solve the problems of XOR. Single-layer perceptron can be improved by multi-layer perceptron, functional perceptron or quadratic function. These solutions are designed and analyzed.
Keywords :
Boolean functions; multilayer perceptrons; neural net architecture; perceptrons; Boolean logic; XOR problem solving; division; functional perceptron; logical operation; multilayer perceptron; quadratic function; single-layer perceptron; Artificial neural networks; Biological neural networks; Electronic mail; Feedforward neural networks; Humans; Linearity; Multilayer perceptrons; Neural networks; Neurons; Performance analysis;
Conference_Titel :
Autonomous Decentralized System, 2002. The 2nd International Workshop on
Print_ISBN :
0-7803-7624-2
DOI :
10.1109/IWADS.2002.1194667