Breaking the Activation Function Bottleneck through Adaptive Parameterization.
Sebastian FlennerhagHujun YinJohn A. KeaneMark ElliotPublished in: NeurIPS (2018)
Keyphrases
- activation function
- neural network
- hidden layer
- back propagation
- artificial neural networks
- feed forward
- feed forward neural networks
- multilayer perceptron
- machine learning
- network size
- basis functions
- neural nets
- training phase
- chaotic neural network
- extreme learning machine
- hidden nodes
- network architecture
- learning rate
- recurrent neural networks
- high dimensional
- pattern recognition
- decision making
- artificial intelligence