αSechSig and αTanhSig: two novel non-monotonic activation functions.
Cemil KözkurtSerhat KiliçarslanSelçuk BasAbdullah ElenPublished in: Soft Comput. (2023)
Keyphrases
- activation function
- neural network
- artificial neural networks
- feed forward
- back propagation
- hidden layer
- complex valued
- neural architecture
- feed forward neural networks
- neural nets
- learning rate
- basis functions
- multilayer perceptron
- hidden nodes
- radial basis function
- network architecture
- rbf neural network
- continuous functions
- machine learning
- multi layer perceptron
- fuzzy neural network
- training phase
- hardware implementation
- convergence speed
- input space
- dynamic programming
- active learning
- reinforcement learning
- feature extraction