Regularization for convolutional kernel tensors to avoid unstable gradient problem in convolutional neural networks.
Pei-Chang GuoPublished in: CoRR (2021)
Keyphrases
- convolutional neural networks
- convolutional network
- reproducing kernel hilbert space
- kernel ridge regression
- positive definite
- kernel machines
- structure tensor
- kernel function
- kernel methods
- kernel matrices
- polynomial kernels
- high order
- regularization parameter
- gaussian processes
- diffusion tensor
- optimal kernel
- gaussian kernels
- feature space
- kernel learning
- regularization term
- semi supervised
- tensor voting
- gaussian process
- magnetic resonance images
- support vector
- kernel based learning methods