Neural Tangent Kernel: Lazy Training, Kernel Equivalence, μP, and the Limits of Width
AdvancedNew
0 answered4 advancedAdapts to your performance
Question 1 of 4
120sadvanced (7/10)conceptual
In the neural tangent kernel (NTK) regime, a neural network behaves like a linear model in function space. When does this regime apply?