TaLK Convolution

2000년 도입 · 논문 1편에서 사용

A Time-aware Large Kernel (TaLK) convolution is a type of temporal convolution that learns the kernel size of a summation kernel for each time-step instead of learning the kernel weights as in a typical convolution operation. For each time-step, a function is responsible for predicting the appropriate size of neighbor representations to use in the form of left and right offsets relative to the time-step.

출처: Time-aware Large Kernel Convolutions

소개 논문: Time-aware Large Kernel Convolutions