On the performance of pairings of activation and loss functions in neural networks.
Rodrigo G. F. SoaresEmeson J. S. PereiraPublished in: IJCNN (2016)
Keyphrases
- loss function
- neural network
- pairwise
- logistic regression
- loss minimization
- empirical risk
- learning to rank
- squared error
- support vector
- reproducing kernel hilbert space
- artificial neural networks
- hinge loss
- risk minimization
- learning models
- back propagation
- update rules
- bayes rule
- convex loss functions
- boosting framework
- boosting algorithms
- feature selection
- pairwise constraints
- search engine
- learning algorithm
- machine learning