flâneur — a map of the web's best reading

Neural tangent kernel - Wikipedia

en.wikipedia.org · 5,667 words · saved by 1 readers

In the study of artificial neural networks (ANNs), the neural tangent kernel (NTK) is a kernel that describes the evolution of deep artificial neural networks during their training by gradient descent. It allows ANNs to be studied using theoretical tools from kernel methods.

Neural tangent kernel - Wikipedia Jump to content From Wikipedia, the free encyclopedia Type of kernel induced by artificial neural networks In the study of artificial neural networks (ANNs), the neural tangent kernel ( NTK ) is a kernel that describes the evolution of deep artificial neural networks during their training by gradient descent . It allows ANNs to be studied using theoretical tools from kernel methods . In general, a kernel is a positive-semidefinite symmetric function of two inputs which represents some notion of similarity between the two inputs. The NTK is a specific kernel de

Explore this link on the map →

related reading