forked from scutan90/DeepLearning-500-questions
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
31 additions
and
14 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -497,20 +497,37 @@ [email protected] (唯一官方邮箱);现出现不法分子冒充发起人 | |
14.3 如何选择调试值? 359 | ||
14.4 为超参数选择合适的范围 359 | ||
14.5 如何搜索超参数? 359 | ||
## 第十五章 正则化 361 | ||
15.1 什么是正则化? 361 | ||
15.2 正则化原理? 361 | ||
15.3 为什么要正则化? 361 | ||
15.4 为什么正则化有利于预防过拟合? 361 | ||
15.5 为什么正则化可以减少方差? 362 | ||
15.6 L2正则化的理解? 362 | ||
15.7 理解dropout 正则化 362 | ||
15.8 有哪些dropout 正则化方法? 362 | ||
15.8 如何实施dropout 正则化 363 | ||
15.9 Python 实现dropout 正则化 363 | ||
15.10 L2正则化和dropout 有什么不同? 363 | ||
15.11 dropout有什么缺点? 363 | ||
15.12 其他正则化方法? 364 | ||
## 第十五章 异构计算, GPU和框架选型指南 361 | ||
15.1 什么是异构计算? 361 | ||
15.2 什么是GPGPU? 361 | ||
15.3 GPU架构简介 361 | ||
15.3.1 为什么要使用GPU? | ||
15.3.2 CUDA 核心是什么? | ||
15.3.3 新图灵架构里的tensor core对深度学习有什么作用? | ||
15.3.4 GPU内存架构和应用性能的联系? | ||
15.4 CUDA 框架 | ||
15.4.1 做CUDA编程难不难? | ||
15.4.2 cuDNN | ||
15.5 GPU硬件环境配置推荐 | ||
15.5.1 GPU主要性能指标 | ||
15.5.2 购买建议 | ||
15.6 软件环境搭建 | ||
15.6.1 操作系统选择? | ||
15.6.2 本机安装还是使用docker? | ||
15.6.3 GPU驱动问题 | ||
15.7 框架选择 | ||
15.7.1 主流框架比较 | ||
15.7.2 框架详细信息 | ||
15.7.3 哪些框架对于部署环境友好? | ||
15.7.4 移动平台的框架如何选择? | ||
15.8 其他 | ||
15.8.1 多GPU环境的配置 | ||
15.8.2 是不是可以分布式训练? | ||
15.8.3 可以在SPARK环境里训练或者部署模型吗? | ||
15.8.4 怎么进一步优化性能? | ||
15.8.5 TPU和GPU的区别? | ||
15.8.6 未来量子计算对于深度学习等AI技术的影像? | ||
|
||
## 参考文献 366 | ||
hey you are looked like a cool developer. | ||
Translate it in english. |