Neural Tangent Transfer

2000년 도입 · 논문 1편에서 사용

Neural Tangent Transfer, or NTT, is a method for finding trainable sparse networks in a label-free manner. Specifically, NTT finds sparse networks whose training dynamics, as characterized by the neural tangent kernel, mimic those of dense networks in function space.

출처: Finding trainable sparse networks through Neural Tangent Transfer

소개 논문: Finding trainable sparse networks through Neural Tangent Transfer