Most Activation Functions Can Win the Lottery Without Excessive Depth.
Rebekka BurkholzPublished in: NeurIPS (2022)
Keyphrases
- activation function
- neural network
- neural architecture
- back propagation
- feed forward
- feed forward neural networks
- artificial neural networks
- complex valued
- hidden layer
- neural nets
- learning rate
- hidden nodes
- multilayer perceptron
- basis functions
- network architecture
- radial basis function
- training phase
- linear combination
- fuzzy neural network
- pattern recognition
- decision making
- artificial intelligence
- machine learning