Loading...
Please wait, while we are loading the content...
Multilayer Perceptron Learning Utilizing Singular Regions and Search Pruning
| Content Provider | Semantic Scholar |
|---|---|
| Author | Satoh, Seiya Nakano, Ryohei |
| Copyright Year | 2013 |
| Abstract | In a search space of a multilayer perceptron having J hidden units, MLP(J), there exist flat areas called singular regions. Since singular regions cause serious stagnation of learning, a learning method to avoid them was once proposed, but was not guaranteed to find excellent solutions. Recently, SSF1.2 was proposed which utilizes singular regions to stably and successively find excellent solutions commensurate with MLP(J). However, SSF1.2 has a problem that it takes longer as J gets larger. This paper proposes a learning method SSF1.3 that enhances SSF1.2 by attaching search pruning so as to discard a search whose route is similar to one of previous searches. Our experiments showed SSF1.3 ran several times faster than SSF1.2 without degrading solution quality. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.iaeng.org/publication/WCECS2013/WCECS2013_pp790-795.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
