Investigating the interaction between gradient-only line searches and different activation functions.
Dominic KafkaDaniel N. WilkePublished in: CoRR (2020)
Keyphrases
- activation function
- neural network
- artificial neural networks
- neural architecture
- back propagation
- feed forward
- feed forward neural networks
- complex valued
- hidden layer
- multilayer perceptron
- neural nets
- learning rate
- hidden nodes
- knn
- basis functions
- fuzzy neural network
- machine learning
- edge detection
- learning algorithm
- decision trees
- network architecture
- active learning
- non stationary
- markov random field