Most Activation Functions Can Win the Lottery Without Excessive Depth.
Rebekka BurkholzPublished in: CoRR (2022)
Keyphrases
- activation function
- neural network
- neural architecture
- artificial neural networks
- feed forward
- hidden layer
- complex valued
- back propagation
- feed forward neural networks
- neural nets
- radial basis function
- multilayer perceptron
- basis functions
- learning rate
- network architecture
- multi layer perceptron
- artificial intelligence
- hidden nodes
- autoregressive
- fuzzy neural network
- training phase
- bp neural network
- recurrent neural networks
- control system
- pattern recognition
- decision trees
- feature selection