How to understand that the dimensions of parameter B are (B,L,N) in mamba?

  Kiến thức lập trình

I want to know that why B as a parameter to selective structure doesn’t include dimension D. In other words, why do author map dimension D to N?

I try to understand it. But the paper doesn’t seem to have a clear explanation about it. I only understand that in order to implement time-varying structure, the B L dimension was added.

LEAVE A COMMENT