一天搞懂机器学习PPT笔记-2
2017-06-22 21:32
344 查看
Tips for Training DNN
minimize total loss
more layers do not imply better
- so it is hard to get the power of deep
Learning rate
popular&simple idea:reduce the learning rate by some factor every few epochs– at the beginning,we are far from the destination,so we use larger learning rate
– after several epochs,we are close to the destination,so we reduce the learning rate.
– a demo rate function:rate = init rate / sqrt(t+1)
– learning rate cannot be one-size-fits-all,so we should give different parameters and different learning rates.
hard to find optimal network parameters
- there are many points where the value of judging the parameters is 0.so we has the Momentum
Momentum
– to make sure that we can find the better parameters
Why Overfitting
training data and testing data can be differentlearning target is trained by the training data
the parameters achieving the learning target do not necessary have good results on the testing data
panacea for OverFitting
have more training datacreate more training data,for example:
some ways to reduce the time to get the better parameters
early Stoppingweight decay
drop out
Variants of Neural Networks
Convolutional Neural Network(Widely used in image processing)Recurrent Neural Network(RNN)
相关文章推荐
- 一天搞懂深度学习—学习笔记2(CNN)
- 一天搞懂深度学习—学习笔记4(knowledge and tricks)
- 李宏毅《一天搞懂深度学习》学习笔记-1
- 干货 | 台大“一天搞懂深度学习”课程PPT(下载方式见文末!!)
- 一天搞懂深度学习—学习笔记3(RNN)
- 一天搞懂深度学习—学习笔记1
- sql学习笔记之月的第一天或者是最后一天
- JUnit学习笔记4---Ant的一天
- 花了一天的工夫才写了一篇PPT
- 阅读笔记-机器学习-第3章-决策树学习
- 敏捷个人9月份活动PPT:敏捷个人和敏捷结果,设计你的一天,设计你的一周
- linux培训课程第十天:ppt以及笔记
- 某linux知识ppt学习笔记一
- [笔记] PPT幻灯片也RIA——PPT实现倒计时功能
- 程序员职场第一课第一章ppt笔记
- 阅读笔记-机器学习-第2章-概念学习和一般到特殊序
- linux培训课程第六天:ppt以及笔记
- linux培训课程第八天:ppt以及笔记
- linux培训课程第十二天:ppt以及笔记
- linux培训课程第九天:ppt以及笔记