Title :
Global optimization of neural network weights using subenergy tunneling function and ripple search
Author :
Ye, Hong ; Lin, Zhiping
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
Abstract :
This paper presents a new approach to supervised training of weights in multilayer feedforward neural networks. The algorithm is based on a subenergy tunneling function to reject searching in unpromising regions and a ripple-like global search to get away from local minima. The global convergence properties of the proposed algorithm are demonstrated through three frequently used neural network learning applications. The performance of the new technique is better than or at least similar to that of other training methods in the literature. The proposed method is flexible and conceptually simple to implement.
Keywords :
feedforward neural nets; learning (artificial intelligence); multilayer perceptrons; optimisation; global convergence properties; global optimization; global search; learning applications; multilayer feedforward neural networks; neural network weights; ripple search; subenergy tunneling function; supervised training; Convergence; Equations; Feedforward neural networks; Multi-layer neural network; Neural networks; Optimization methods; Space exploration; Stochastic processes; Supervised learning; Tunneling;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1206415