Module deep_learning_kernels

Module deep_learning_kernels 

Source
Expand description

Deep Learning Integration for Kernel Approximation

This module implements advanced kernel methods inspired by deep learning, including Neural Tangent Kernels (NTK), Deep Kernel Learning, and infinite-width network approximations.

§References

  • Jacot et al. (2018): “Neural Tangent Kernel: Convergence and Generalization in Neural Networks”
  • Wilson et al. (2016): “Deep Kernel Learning”
  • Lee et al. (2018): “Deep Neural Networks as Gaussian Processes”
  • Arora et al. (2019): “Exact solutions to the nonlinear dynamics of learning in deep linear neural networks”

Structs§

DKLConfig
Deep Kernel Learning combines deep neural networks with kernel methods
DeepKernelLearning
InfiniteWidthKernel
Infinite-Width Network Kernel
NTKConfig
Configuration for Neural Tangent Kernel
NeuralTangentKernel
Neural Tangent Kernel (NTK) Approximation

Enums§

Activation
Activation functions for neural network kernels