TSSR: A Truncated and Signed Square Root Activation Function for Neural Networks.
Yuanhao GongPublished in: CoRR (2023)
Keyphrases
- activation function
- square root
- neural network
- back propagation
- hidden layer
- artificial neural networks
- feed forward
- feed forward neural networks
- kalman filtering
- neural nets
- floating point
- multilayer perceptron
- feedforward neural networks
- arrival rate
- euclidean space
- learning rate
- radial basis function
- probability density function
- network architecture
- fuzzy neural network
- training phase
- multi layer perceptron
- neural network model
- fuzzy logic
- extreme learning machine
- rbf neural network
- riemannian manifolds
- recurrent neural networks
- fault diagnosis
- pattern recognition
- dynamical systems
- model selection