Using genetic algorithms to select architecture of a feedforward artificial neural network
| dc.citation.epage | 594 | en_US |
| dc.citation.issueNumber | 3-4 | en_US |
| dc.citation.spage | 574 | en_US |
| dc.citation.volumeNumber | 289 | en_US |
| dc.contributor.author | Arifovic, J. | en_US |
| dc.contributor.author | Gençay, R. | en_US |
| dc.date.accessioned | 2016-02-08T10:35:57Z | |
| dc.date.available | 2016-02-08T10:35:57Z | |
| dc.date.issued | 2001 | en_US |
| dc.department | Department of Economics | en_US |
| dc.description.abstract | This paper proposes a model selection methodology for feedforward network models based on the genetic algorithms and makes a number of distinct but inter-related contributions to the model selection literature for the feedforward networks. First, we construct a genetic algorithm which can search for the global optimum of an arbitrary function as the output of a feedforward network model. Second, we allow the genetic algorithm to evolve the type of inputs, the number of hidden units and the connection structure between the inputs and the output layers. Third, we study how introduction of a local elitist procedure which we call the election operator affects the algorithm's performance. We conduct a Monte Carlo simulation to study the sensitiveness of the global approximation properties of the studied genetic algorithm. Finally, we apply the proposed methodology to the daily foreign exchange returns. | en_US |
| dc.description.provenance | Made available in DSpace on 2016-02-08T10:35:57Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2001 | en |
| dc.identifier.doi | 10.1016/S0378-4371(00)00479-9 | en_US |
| dc.identifier.eissn | 1873-2119 | |
| dc.identifier.issn | 0378-4371 | |
| dc.identifier.uri | http://hdl.handle.net/11693/24903 | |
| dc.language.iso | English | en_US |
| dc.publisher | Elsevier BV | en_US |
| dc.relation.isversionof | http://dx.doi.org/10.1016/S0378-4371(00)00479-9 | en_US |
| dc.source.title | Physica A : Statistical Mechanics and its Applications | en_US |
| dc.subject | Model selection | en_US |
| dc.subject | Genetic algorithms | en_US |
| dc.subject | Mathematical models | en_US |
| dc.subject | Monte Carlo methods | en_US |
| dc.subject | Foreign exchange returns | en_US |
| dc.subject | Neural networks | en_US |
| dc.title | Using genetic algorithms to select architecture of a feedforward artificial neural network | en_US |
| dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Using genetic algorithms to select architecture of a feedforward artificial neural network.pdf
- Size:
- 125.62 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version