20.74 MB
13-9 BERT模型训练方法.mp42022-05-10
22.55 MB
13-8 transformer整体架构梳理.mp42022-05-10
17.16 MB
13-7 位置编码与多层堆叠.mp42022-05-10
20.10 MB
13-6 Multi-head的作用.mp42022-05-10
21.35 MB
13-5 特征分配与softmax机制.mp42022-05-10
23.89 MB
13-4 self-attention计算方法.mp42022-05-10
15.95 MB
13-3 注意力机制的作用.mp42022-05-10
23.32 MB
13-2 传统解决方案遇到的问题.mp42022-05-10
23.51 MB
13-10 训练实例.mp42022-05-10
11.28 MB
13-1 BERT任务目标概述.mp42022-05-10