At , it does not look like all the "paths" share the same weights - except for the last layer (just before the output.) But he says they use the same kernels. I guess the illustration is maybe a bit misleading and the truth is that they do indeed share weights?(00:39:23 - 01:28:48)
Week 6 – Lecture: CNN applications, RNN, and attention
Alfredo Canziani
※本サイトに掲載されているチャンネル情報や動画情報はYouTube公式のAPIを使って取得・表示しています。
Timetable
動画タイムテーブル