IEEE Transactions on Neural Networks · 2003 · 787 citations · 30 references
ComputingComputer ScienceArtificial IntelligenceForecastingMachine LearningEvolutionary ComputationEvolutionary OptimizationGenetic AlgorithmsNeural NetworksPopulation-based SearchTime Series ForecastingEvolutionary Optimization For TuningFeedforward Neural NetworksGenetic Algorithm OptimizationGenetic Algorithm Parameter TuningNeural ForecastingNeural Network ModelingNeural Network PredictionNeural Network-based Tuning
This paper presents the tuning of the structure and parameters of a neural network using an improved genetic algorithm (GA). It is also shown that the improved GA performs better than the standard GA based on some benchmark test functions. A neural network with switches introduced to its links is proposed. By doing this, the proposed neural network can learn both the input-output relationships of an application and the network structure using the improved GA. The number of hidden nodes is chosen manually by increasing it from a small number until the learning performance in terms of fitness value is good enough. Application examples on sunspot forecasting and associative memory are given to show the merits of the improved GA and the proposed neural network.
30
Evolutionary programming made faster
Xin Yao, Yong Liu, Guangming Lin · IEEE Transactions on Evolutionary Computation · 1999 · 3.9K citations
Evolving artificial neural networks
Xin Yao · Proceedings of the IEEE · 1999 · 3K citations
M. Srinivas, L.M. Patnaik · Computer · 1994 · 2.2K citations
An Analysis Of The Behavior Of A Class Of Genetic Adaptive Systems.
Kenneth DeJong · Deep Blue (University of Michigan) · 1975 · 1.3K citations · Full text
Life Sciences, Biology, Genetics +12