| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| 线性回归的简洁实现 |
|
57 | 13412 | June 9, 2023 |
| 概率 |
|
51 | 7685 | June 9, 2023 |
| 数值稳定性和模型初始化 |
|
11 | 2239 | June 9, 2023 |
| Large-Scale Pretraining with Transformers |
|
4 | 506 | June 8, 2023 |
| 如何处理练习题 |
|
0 | 15 | June 8, 2023 |
| 线性回归的简洁实现 |
|
2 | 1074 | June 8, 2023 |
| 多层感知机的从零实现 |
|
62 | 8322 | June 8, 2023 |
| 使用 GPU |
|
26 | 3900 | June 7, 2023 |
| 概率 |
|
9 | 1409 | June 7, 2023 |
| 微分 |
|
16 | 2715 | June 7, 2023 |
| Probability |
|
29 | 2861 | June 7, 2023 |
| 数据预处理 |
|
100 | 15476 | June 7, 2023 |
| 线性回归的从零开始实现 |
|
106 | 19867 | June 7, 2023 |
| 引言 |
|
22 | 9214 | June 7, 2023 |
| 多GPU的简洁实现 |
|
8 | 1586 | June 7, 2023 |
| Python 3.11 安装d2l出错 |
|
1 | 51 | June 6, 2023 |
| Transformer |
|
23 | 4325 | June 6, 2023 |
| Softmax回归的从零实现 |
|
109 | 13784 | June 6, 2023 |
| 多GPU训练 |
|
9 | 1208 | June 5, 2023 |
| 注意力评分函数 |
|
12 | 1588 | June 5, 2023 |
| 批量规范化 |
|
30 | 4196 | June 4, 2023 |
| 自动并行 |
|
5 | 542 | June 4, 2023 |
| 异步计算 |
|
3 | 911 | June 4, 2023 |
| 编译器和解释器 |
|
8 | 1296 | June 4, 2023 |
| 为什么要清掉模型的梯度呢 |
|
0 | 35 | June 4, 2023 |
| 注意力汇聚：Nadaraya-Watson 核回归 |
|
24 | 4419 | June 4, 2023 |
| Bidirectional Encoder Representations from Transformers (BERT) |
|
4 | 923 | June 3, 2023 |
| 使用块的网络（VGG） |
|
39 | 5875 | June 3, 2023 |
| 风格迁移 |
|
7 | 1402 | June 3, 2023 |
| Question regarding math in general |
|
0 | 27 | June 2, 2023 |