ckn_kernel: Convolutional kernel computation (CKN, NTK). Package for computing exact kernel evaluations for some convolutional kernels, such as those from convolutional kernel networks (CKNs, see here, here, here) and neural tangent kernels for convolutional networks (NTK or CNTK, see here, here, here). The main code is in C++, with Cython bindings.
Keywords for this software
References in zbMATH (referenced in 5 articles , 1 standard article )
Showing results 1 to 5 of 5.
- Cahill, Jameson; Contreras, Andres; Contreras-Hip, Andres: Complete set of translation invariant measurements with Lipschitz bounds (2020)
- Rousseau, François; Drumetz, Lucas; Fablet, Ronan: Residual networks as flows of diffeomorphisms (2020)
- Sheng, Baohuai; Liu, Huanxiang; Wang, Huimin: Learning rates for the kernel regularized regression with a differentiable strongly convex loss (2020)
- Bietti, Alberto; Mairal, Julien: Group invariance, stability to deformations, and complexity of deep convolutional representations (2019)
- Geete, Kanu; Pandey, Manish: A noise-based stabilizer for convolutional neural networks (2019)