learning
/
DeepLearning-500-questions
mirror of https://github.com/scutan90/DeepLearning-500-questions.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

edit some

This commit is contained in:
KeyForce 2018-11-24 21:05:46 +08:00
parent 2744646819
commit 339e7adf47
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ch11_迁移学习/第十一章_迁移学习.md
View File

@ -37,9 +37,9 @@
- **基于模型的迁移 (Parameter based TL)**：利用源域和目标域的参数共享模型
- **基于关系的迁移 (Relation based TL)**：利用源域中的逻辑网络关系进行迁移
![1542972502781](E:/Project%20Station/DeepLearning-500-questions/ch11_%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0/img/ch11/1542972502781.png)
![1542972502781](./img/ch11/1542972502781.png)
![1542974131814](E:/Project%20Station/DeepLearning-500-questions/ch11_%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0/img/ch11/1542974131814.png)
![1542974131814](./img/ch11/1542974131814.png)
## 10.4 迁移学习与传统机器学习有什么区别？（KeyFoece）
@ -49,7 +49,7 @@
| 数据标签 | 不需要足够的数据标注 | 足够的数据标注 |
| 建模 | 可以重用之前的模型 | 每个任务分别建模 |
![1542973960796](E:/Project%20Station/DeepLearning-500-questions/ch11_%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0/img/ch11/1542973960796.png)
![1542973960796](./img/ch11/1542973960796.png)
## 10.5 迁移学习的基本思路？（中科院计算所-王晋东）