Linearized sigmoidal activation: A novel activation function with tractable non-linear characteristics to boost representation capability.
Vivek Singh BawaVinay KumarPublished in: Expert Syst. Appl. (2019)
Keyphrases
- activation function
- neural network
- artificial neural networks
- feed forward neural networks
- feed forward
- back propagation
- learning rate
- neural nets
- hidden layer
- network size
- feedforward neural networks
- hidden nodes
- single hidden layer
- chaotic neural network
- radial basis function
- extreme learning machine
- sigmoid function
- fuzzy neural network
- multilayer perceptron
- training phase
- input space
- basis functions
- input output
- artificial intelligence
- genetic algorithm