Sigmoid and Beyond: Algebraic Activation Functions for Artificial Neural Networks Based on Solutions of a Riccati Equation.
Nicholas E. ProtonotariosAthanassios S. FokasGeorge A. KastisNikolaos DikaiosPublished in: IT Prof. (2022)
Keyphrases
- activation function
- artificial neural networks
- neural network
- back propagation
- feed forward neural networks
- hidden layer
- hidden neurons
- feed forward
- multilayer perceptron
- neural nets
- neural architecture
- neural network model
- computational intelligence
- multi layer perceptron
- radial basis function
- genetic algorithm
- genetic algorithm ga
- learning rate
- sigmoid function
- basis functions
- differential equations
- network architecture
- mathematical model
- linear combination
- small number
- fuzzy logic
- high dimensional
- learning algorithm