中文版
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| 层和块 |
|
2 | 1654 | January 27, 2023 |
| 网络中的网络（NiN） |
|
2 | 965 | January 12, 2023 |
| 请问实现 d2l-zh 的 CI 有哪些环境要求？ |
|
0 | 603 | December 11, 2022 |
| 硬件 |
|
2 | 1770 | December 9, 2022 |
| 自然语言推断：微调BERT |
|
0 | 744 | November 21, 2022 |
| 多GPU的简洁实现 |
|
0 | 744 | November 22, 2022 |
| 多GPU训练 |
|
0 | 786 | November 22, 2022 |
| 自动并行 |
|
0 | 593 | November 22, 2022 |
| 异步计算 |
|
0 | 806 | November 22, 2022 |
| 编译器和解释器 |
|
0 | 626 | November 22, 2022 |
| 学习率调度器 |
|
0 | 580 | November 22, 2022 |
| Adam算法 |
|
0 | 616 | November 22, 2022 |
| Adadelta |
|
0 | 724 | November 22, 2022 |
| RMSProp算法 |
|
0 | 671 | November 22, 2022 |
| AdaGrad算法 |
|
0 | 577 | November 22, 2022 |
| 动量法 |
|
0 | 512 | November 22, 2022 |
| 小批量随机梯度下降 |
|
0 | 530 | November 22, 2022 |
| 随机梯度下降 |
|
0 | 689 | November 22, 2022 |
| 梯度下降 |
|
0 | 703 | November 22, 2022 |
| 凸性 |
|
0 | 613 | November 22, 2022 |
| 优化和深度学习 |
|
0 | 720 | November 22, 2022 |
| Transformer |
|
0 | 587 | November 22, 2022 |
| 自注意力和位置编码 |
|
0 | 603 | November 22, 2022 |
| 多头注意力 |
|
0 | 762 | November 22, 2022 |
| Bahdanau 注意力 |
|
0 | 570 | November 22, 2022 |
| 注意力评分函数 |
|
0 | 585 | November 22, 2022 |
| 注意力汇聚：Nadaraya-Watson 核回归 |
|
0 | 902 | November 22, 2022 |
| 注意力提示 |
|
0 | 648 | November 22, 2022 |
| 序列到序列学习 |
|
0 | 671 | November 22, 2022 |
| 编码器-解码器架构 |
|
0 | 617 | November 22, 2022 |