ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions.
Koushik BiswasSandeep KumarShilpak BanerjeeAshish Kumar PandeyPublished in: AAAI (2022)
Keyphrases
- activation function
- neural network
- artificial neural networks
- feed forward
- back propagation
- complex valued
- hidden layer
- feed forward neural networks
- neural architecture
- multilayer perceptron
- learning rate
- neural nets
- radial basis function
- network architecture
- basis functions
- hidden nodes
- fuzzy neural network
- feature extraction
- bp neural network
- multi layer perceptron
- low dimensional
- fuzzy logic