Why TanH is a Hardware Friendly Activation Function for CNNs.
Kamel AbdelouahabMaxime PelcatFrançois BerryPublished in: ICDSC (2017)
Keyphrases
- activation function
- neural network
- hidden layer
- back propagation
- artificial neural networks
- feed forward
- feed forward neural networks
- hardware implementation
- cellular neural networks
- multilayer perceptron
- learning rate
- real time
- neural nets
- network architecture
- hidden nodes
- feedforward neural networks
- basis functions
- sigmoid function
- network size
- chaotic neural network
- radial basis function
- fuzzy neural network
- signal processing
- rbf neural network
- multi layer perceptron
- particle swarm optimization