Abstract | ||
---|---|---|
A framework for predictive, on-line, learning networks composed of multiple echo state networks is presented. These composite networks permit learning predictions based on complex combinations of sub-predictions and error terms. The configuration space is explored with a genetic algorithm and better performance is achieved than with hand coded solutions. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-89694-4_56 | SEAL |
Keywords | Field | DocType |
composite network,complex combination,genetic algorithm,composite echo state networks,multiple echo state network,time series prediction,configuration space,better performance,error term,echo state network | Time series,Spectral radius,Computer science,Composite number,Echo state network,Artificial intelligence,Machine learning,Genetic algorithm,Configuration space | Conference |
Volume | ISSN | Citations |
5361 | 0302-9743 | 1 |
PageRank | References | Authors |
0.37 | 6 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Russell Y. Webb | 1 | 6 | 2.86 |