Name
Title | ||
|---|---|---|
Multiobjective Evolutionary Optimization of Training and Topology of Recurrent Neural Networks for Time-Series Prediction |
Abstract | ||
|---|---|---|
This paper provides a new evolutionary multiobjective optimization method for automatically optimizing the network topology of recurrent neural networks (NNs). To obtain NNs with higher prediction capability for time-series data, the proposed method is constructed by focusing on the intensively exploration of a feasible region including solutions with small training errors on the Pareto frontier, unlike existing evolutionary multiobjective optimization methods, which aim to find a whole set of the Pareto optimal solutions. Our method is characterized by the ideas of self-adaptive mutation probability setting, elite preservation strategies and archive for the preservation of local optimal solutions. Through the comparison with the performances of the most promising existing method by Delgado et al. using benchmark time-series data instances, it is shown that the proposed method is superior to the existing effective algorithm with respect to the capability of time-series prediction. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1093/comjnl/bxr042 | Information Science and Applications |
Keywords | Field | DocType |
pareto optimal solution,time-series prediction,time-series data,recurrent neural networks,elite preservation strategy,promising existing method,evolutionary multiobjective optimization method,existing effective algorithm,multiobjective evolutionary optimization,benchmark time-series data instance,pareto frontier,recurrent neural network,network topology,data models,wind speed,pareto analysis,time series prediction,computer networks,numerical analysis,evolutionary computation,predictive models,neural networks,handwriting recognition,topology,artificial neural networks | Data modeling,Mathematical optimization,Computer science,Evolutionary computation,Recurrent neural network,Multi-objective optimization,Network topology,Artificial intelligence,Pareto analysis,Artificial neural network,Pareto principle | Journal |
Volume | Issue | ISSN |
55 | 3 | 0010-4620 |
ISBN | Citations | PageRank |
978-1-4244-5941-4 | 3 | 0.44 |
References | Authors | |
14 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hideki Katagiri | 1 | 436 | 46.48 |
| Ichiro Nishizaki | 2 | 443 | 42.37 |
| Tomohiro Hayashida | 3 | 29 | 11.56 |
| Takanori Kadoma | 4 | 3 | 0.44 |