SQNL: A New Computationally Efficient Activation Function.
Adedamola WuraolaNitish D. PatelPublished in: IJCNN (2018)
Keyphrases
- activation function
- computationally efficient
- neural network
- artificial neural networks
- back propagation
- hidden layer
- feed forward
- feed forward neural networks
- learning rate
- chaotic neural network
- neural nets
- network size
- multilayer perceptron
- basis functions
- radial basis function
- feedforward neural networks
- computational complexity
- training phase
- network architecture
- sigmoid function
- hidden nodes
- linear combination
- multi layer perceptron