Parametric Flatten-T Swish: An Adaptive Non-linear Activation Function For Deep Learning.
Hock Hung ChiengNoorhaniza WahidPauline OngPublished in: CoRR (2020)
Keyphrases
- deep learning
- activation function
- neural network
- feed forward
- artificial neural networks
- unsupervised learning
- hidden layer
- machine learning
- back propagation
- neural nets
- learning rate
- network architecture
- parametric models
- basis functions
- multilayer perceptron
- radial basis function
- multi layer perceptron
- mental models
- training phase
- rbf neural network
- weakly supervised
- fuzzy neural network
- active learning
- reinforcement learning
- computer vision