Dynamic topology generation of an artificial neural network of the multilayer perceptron type
This paper deals with an approximate constructive method to find architectures of artificial neuronal network (ANN) of the type Multi-Layer Percetron (MLP) which solves a particular problem. This method is supplemented with the technique of the Forced search of better local minima. The training of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad de Antioquia
2006-08-01
|
| Series: | Revista Facultad de Ingeniería Universidad de Antioquia |
| Subjects: | |
| Online Access: | https://revistas.udea.edu.co/index.php/ingenieria/article/view/343285 |
| _version_ | 1797861605356077056 |
|---|---|
| author | Héctor Tabares John Branch Jaime Valencia |
| author_facet | Héctor Tabares John Branch Jaime Valencia |
| author_sort | Héctor Tabares |
| collection | DOAJ |
| description |
This paper deals with an approximate constructive method to find architectures of artificial neuronal network (ANN) of the type Multi-Layer Percetron (MLP) which solves a particular problem. This method is supplemented with the technique of the Forced search of better local minima. The training of the net uses an algorithm basic descending gradient (BDG). Techniques such as repetition of the training and the early stopping (cross validation) are used to improve the results. The evaluation approach is based not only on the learning abilities but also on the generalization of the specific generated architectures of a domain. Experimental results are presented in order to prove the effectiveness of the proposed method. These are compared with architectures found by other methods.
|
| first_indexed | 2024-04-09T22:05:49Z |
| format | Article |
| id | doaj.art-27f7cd2694d746fd993226dd0afb5981 |
| institution | Directory Open Access Journal |
| issn | 0120-6230 2422-2844 |
| language | English |
| last_indexed | 2024-04-09T22:05:49Z |
| publishDate | 2006-08-01 |
| publisher | Universidad de Antioquia |
| record_format | Article |
| series | Revista Facultad de Ingeniería Universidad de Antioquia |
| spelling | doaj.art-27f7cd2694d746fd993226dd0afb59812023-03-23T12:38:15ZengUniversidad de AntioquiaRevista Facultad de Ingeniería Universidad de Antioquia0120-62302422-28442006-08-013810.17533/udea.redin.343285Dynamic topology generation of an artificial neural network of the multilayer perceptron typeHéctor Tabares0John Branch1 Jaime Valencia2Universidad de AntioquiaUniversidad Nacional de Colombia Sede MedellínUniversidad de Antioquia This paper deals with an approximate constructive method to find architectures of artificial neuronal network (ANN) of the type Multi-Layer Percetron (MLP) which solves a particular problem. This method is supplemented with the technique of the Forced search of better local minima. The training of the net uses an algorithm basic descending gradient (BDG). Techniques such as repetition of the training and the early stopping (cross validation) are used to improve the results. The evaluation approach is based not only on the learning abilities but also on the generalization of the specific generated architectures of a domain. Experimental results are presented in order to prove the effectiveness of the proposed method. These are compared with architectures found by other methods. https://revistas.udea.edu.co/index.php/ingenieria/article/view/343285Artificial neural networksmulti-layer perceptrontopologyarchitecture |
| spellingShingle | Héctor Tabares John Branch Jaime Valencia Dynamic topology generation of an artificial neural network of the multilayer perceptron type Revista Facultad de Ingeniería Universidad de Antioquia Artificial neural networks multi-layer perceptron topology architecture |
| title | Dynamic topology generation of an artificial neural network of the multilayer perceptron type |
| title_full | Dynamic topology generation of an artificial neural network of the multilayer perceptron type |
| title_fullStr | Dynamic topology generation of an artificial neural network of the multilayer perceptron type |
| title_full_unstemmed | Dynamic topology generation of an artificial neural network of the multilayer perceptron type |
| title_short | Dynamic topology generation of an artificial neural network of the multilayer perceptron type |
| title_sort | dynamic topology generation of an artificial neural network of the multilayer perceptron type |
| topic | Artificial neural networks multi-layer perceptron topology architecture |
| url | https://revistas.udea.edu.co/index.php/ingenieria/article/view/343285 |
| work_keys_str_mv | AT hectortabares dynamictopologygenerationofanartificialneuralnetworkofthemultilayerperceptrontype AT johnbranch dynamictopologygenerationofanartificialneuralnetworkofthemultilayerperceptrontype AT jaimevalencia dynamictopologygenerationofanartificialneuralnetworkofthemultilayerperceptrontype |