Constructive function approximation by neural networks with optimized activation functions and fixed weights.
Feng-Jun LiPublished in: Neural Comput. Appl. (2019)
Keyphrases
- activation function
- function approximation
- hidden nodes
- neural network
- radial basis function
- connection weights
- hidden layer
- artificial neural networks
- multilayer perceptron
- feed forward neural networks
- back propagation
- reinforcement learning
- rbf network
- feed forward
- neural nets
- basis functions
- function approximators
- linear combination
- multi layer perceptron
- rbf neural network
- learning rate
- network architecture
- fuzzy neural network
- learning tasks
- pattern recognition
- genetic algorithm
- support vector machine svm
- recurrent neural networks
- rbfnn
- control system
- evolutionary algorithm
- support vector