Name
Title | ||
|---|---|---|
Parametric optimization of artificial neural networks for signal approximation applications |
Abstract | ||
|---|---|---|
Artificial neural networks are used to solve diverse sets of problems. However, the accuracy of the network's output for a given problem domain depends on appropriate selection of training data as well as various design parameters that define the structure of the network before it is trained. Genetic algorithms have been used successfully for many types of optimization problems. In this paper, we describe a methodology that uses genetic algorithms to find an optimal set of configuration parameters for artificial neural networks such that the network's approximation error for signal approximation problems is minimized. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1145/2016039.2016095 | ACM Southeast Regional Conference 2005 |
Keywords | Field | DocType |
configuration parameter,training data,signal approximation problem,genetic algorithm,appropriate selection,approximation error,signal approximation application,optimization problem,parametric optimization,artificial neural network,problem domain,diverse set,artificial neural networks,genetic algorithms | Intelligent control,Mathematical optimization,Computer science,Test functions for optimization,Stochastic neural network,Recurrent neural network,Types of artificial neural networks,Artificial intelligence,Deep learning,Artificial neural network,Optimization problem | Conference |
Citations | PageRank | References |
1 | 0.40 | 3 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| J. Lane Thames | 1 | 42 | 3.70 |
| Randal Abler | 2 | 52 | 6.72 |
| Dirk Schaefer | 3 | 29 | 2.63 |