Title :
Training Multilayer Neural Network by Global Chaos Optimization Algorithms
Author :
Khoa, T.Q.D. ; Nakagawa, Masahiro
Author_Institution :
Nagaoka Univ. of Technol., Niigata
Abstract :
Fractals and chaos are novel fields of physics and mathematics showing up a new way of universe viewpoint and creating many ideas to solve several present problems. In this paper, a novel algorithm based on the chaotic sequence generator with the highest ability to adapt and reach the global optima is proposed. The adaptive ability of proposal algorithm is flexible in 2 procedures. The first one is Breadth-first search and the second one is Depth-first search. The proposal algorithm is examined by 2 functions, the Camel function and the Schaffer function. Furthermore, the proposal algorithm is applied to optimize training Multilayer Neural Networks.
Keywords :
chaos; fractals; learning (artificial intelligence); multilayer perceptrons; optimisation; tree searching; Camel function; Schaffer function; breadth-first search; chaotic sequence generator; depth-first search; fractals; global chaos optimization; global optima; multilayer neural network; Backpropagation algorithms; Chaos; Convergence; Fractals; Genetic algorithms; Mathematics; Multi-layer neural network; Neural networks; Optimization methods; Proposals; Chaos and fractals; Evolution programming; Multilayer Neural Networks; Nonlinear optimization; chaos optimization algorithm;
Conference_Titel :
Neural Networks, 2007. IJCNN 2007. International Joint Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4244-1379-9
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2007.4370944
