An improved learning algorithm for random neural networks based on particle swarm optimization and input-to-output sensitivity.
Qing-Hua LingYuqing SongFei HanConghua ZhouHu LuPublished in: Cogn. Syst. Res. (2019)
Keyphrases
- particle swarm optimization
- hidden units
- neural network
- rbf network
- desired output
- learning algorithm
- back propagation
- input data
- radial basis function
- input variables
- multiple output
- feed forward neural networks
- nonlinear functions
- neural network structure
- artificial neural networks
- pso algorithm
- pattern recognition
- hidden layer
- genetic algorithm
- particle swarm optimization algorithm
- rbf neural network
- multilayer perceptron
- training data
- global optimization
- control signals
- input pattern
- particle swarm optimization pso
- learning rules
- training algorithm
- sensitivity analysis
- feed forward
- number of hidden units
- fuzzy logic
- self organizing maps
- differential evolution
- swarm intelligence
- neural network model
- particle swarm
- fuzzy systems
- multi layer
- recurrent neural networks
- reinforcement learning
- learning tasks
- activation function
- learning problems
- ant colony optimization
- neural nets
- output space
- bayes rule
- control system