Abstract | ||
---|---|---|
Due to the complex nature of training neural network (NN), this problem has gained popularity in the nonlinear optimization field. In order to avoid falling into local minimum because of inappropriate initial weights, a number of global search techniques are developed. This paper applies a novel global algorithm, which is electromagnetism-like mechanism (EM) algorithm, to train NN and the EM based algorithm for neural network training is presented. The performance of the proposed algorithm is evaluated in classification problems and the comparison with BP and GA algorithms shows its effectiveness. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-85984-0_5 | ICIC (2) |
Keywords | Field | DocType |
neural network training,novel global algorithm,ga algorithm,complex nature,inappropriate initial weight,electromagnetism-like mechanism,classification problem,proposed algorithm,training neural network,global search technique,nonlinear optimization,neural network,em algorithm | Computer science,Nonlinear programming,Electromagnetism,Algorithm,Time delay neural network,Artificial intelligence,Local search (optimization),Artificial neural network,Population-based incremental learning,Machine learning | Conference |
Volume | ISSN | Citations |
5227 | 0302-9743 | 6 |
PageRank | References | Authors |
0.56 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiao-Juan Wang | 1 | 22 | 8.34 |
Liang Gao | 2 | 1493 | 128.41 |
Chaoyong Zhang | 3 | 320 | 23.22 |