V-shaped neurons in hidden layer of ANN universal approximator without flat domains.
Josef BostikMartin KlimtMatej MojzesJaromír KukalIvo BukovskyMatous CejnekPublished in: IJCNN (2016)
Keyphrases
- hidden layer
- artificial neural networks
- back propagation
- feed forward
- feed forward neural networks
- neural network
- multilayer perceptron
- radial basis function
- recurrent neural networks
- activation function
- neural nets
- learning rate
- receptive fields
- feedforward neural networks
- connection weights
- rbf neural network
- output layer
- training algorithm
- latent variables
- fuzzy neural network
- hidden neurons
- bp neural network
- artificial intelligence
- machine learning
- input output
- fuzzy logic
- hidden nodes
- genetic algorithm