Name
Title | ||
|---|---|---|
Problems and Features of Evolutionary Algorithms to Build Hybrid Training Methods for Recurrent Neural Networks |
Abstract | ||
|---|---|---|
Dynamical recurrent neural networks are models suitable to solve problems where the input and output data may have dependencies in time, like grammatical inference or time series prediction. However, traditional training algorithms for these networks sometimes provide unsuitable results because of the vanishing gradient problems. This work focuses on hybrid proposals of training algorithms for this type of neural networks. The methods studied are based on the combination of heuristic procedures with gradient-based algorithms. In the experimental section, we show the advantages and disadvantages that we may find when using these training techniques in time series prediction problems, and provide a general discussion about the problems and cases of different hybridations based on genetic evolutionary algorithms. |
Year | Venue | Keywords |
|---|---|---|
2007 | ICEIS 2007: PROCEEDINGS OF THE NINTH INTERNATIONAL CONFERENCE ON ENTERPRISE INFORMATION SYSTEMS: INFORMATION SYSTEMS ANALYSIS AND SPECIFICATION | recurrent neural network,hybrid algorithms,time series |
Field | DocType | Citations |
Intelligent control,Evolutionary acquisition of neural topologies,Evolutionary algorithm,Computer science,Recurrent neural network,Time delay neural network,Types of artificial neural networks,Artificial intelligence,Deep learning,Evolutionary programming,Machine learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| M. P. Cuéllar | 1 | 161 | 11.53 |
| Miguel Delgado | 2 | 106 | 7.81 |
| Marial del Carmen Pegalajar Jiménez | 3 | 13 | 2.21 |