SinP[N]: A Fast Convergence Activation Function for Convolutional Neural Networks.
Ka-Hou ChanSio Kei ImWei KeNgan-Lin LeiPublished in: UCC Companion (2018)
Keyphrases
- differential evolution
- activation function
- convolutional neural networks
- convergence speed
- learning rate
- neural network
- hidden layer
- convolutional network
- artificial neural networks
- genetic algorithm
- feed forward neural networks
- feed forward
- network architecture
- multilayer perceptron
- chaotic neural network
- network size
- neural nets
- back propagation
- convergence rate
- basis functions
- feedforward neural networks
- sigmoid function
- hidden nodes
- fuzzy neural network
- pattern recognition
- reinforcement learning
- extreme learning machine
- probabilistic model
- training phase
- rbf neural network
- radial basis function