EIS - a family of activation functions combining Exponential, ISRU, and Softplus.
Koushik BiswasSandeep KumarShilpak BanerjeeAshish Kumar PandeyPublished in: CoRR (2020)
Keyphrases
- activation function
- neural network
- neural architecture
- artificial neural networks
- feed forward
- complex valued
- hidden layer
- learning rate
- neural nets
- back propagation
- multilayer perceptron
- feed forward neural networks
- radial basis function
- network architecture
- training phase
- probabilistic model
- evolutionary algorithm
- continuous functions
- high dimensional
- hidden nodes
- expert systems