Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks.
Blake BordelonCengiz PehlevanPublished in: CoRR (2022)
Keyphrases
- neural network
- pattern recognition
- kernel function
- theoretical framework
- wide range
- general theory
- theoretical basis
- support vector
- feature space
- artificial neural networks
- fuzzy logic
- back propagation
- von neumann
- kernel learning
- mathematical theory
- fuzzy systems
- input space
- recurrent neural networks
- feed forward
- kernel methods
- image segmentation
- information systems
- social networks
- artificial intelligence
- machine learning