Towards a General Theory of Infinite-Width Limits of Neural Classifiers.
Eugene A. GolikovPublished in: ICML (2020)
Keyphrases
- general theory
- neural classifier
- neural network
- morphological operators
- training data
- support vector
- network architecture
- decision trees
- learning rules
- mathematical theory
- stable models
- feature selection
- databases
- training set
- fuzzy logic
- feature set
- belief functions
- support vector machine
- data model
- object recognition
- image segmentation