Title :
On the selection of nodes in linear-in-the-weight neural networks
Author :
Kosmatopoulos, Elias B. ; Dimopoulos, Nikitas J.
Author_Institution :
Dept. of Electr. Eng. Syst., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
In this paper, we propose algorithms for selecting the regressor terms in linear-in-the-weight neural networks. These algorithms are accompanied by appropriate learning algorithms for adjusting the weights of the neural network. By analyzing an appropriate error functional, we investigate the convergence properties of the proposed algorithms; moreover, we investigate the optimality of these algorithms and we construct conditions-regarding the nature of the regressor terms-under which the proposed algorithms are optimal
Keywords :
convergence of numerical methods; function approximation; learning (artificial intelligence); neural nets; optimisation; convergence; error functional; function approximation; learning algorithms; neural networks; node selection; optimisation; regressor; weight adjustment; Adaptive systems; Algorithm design and analysis; Convergence; Error analysis; Fuzzy systems; Intelligent networks; Multi-layer neural network; Neural networks; Power system modeling; RNA;
Conference_Titel :
Communications, Computers and Signal Processing, 1997. 10 Years PACRIM 1987-1997 - Networking the Pacific Rim. 1997 IEEE Pacific Rim Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
0-7803-3905-3
DOI :
10.1109/PACRIM.1997.620377
