CS224d Problem set 1作业
2015-07-26 21:24
344 查看
欢迎转载,转载注明出处:
http://blog.csdn.net/neighborhoodguo/article/details/47071597
编程题里的negative sampling和第三题(a)的推导过程类似,所以就没有重新推导了
4.(a)Because over-fitting will make out model have a poor generalized error and overfit the training set. In order to improve our model's accuracy, we should introduce regularization to avoid over-fitting.
(b)That is a "v" curve shape, since less regularization will lead to under-fitting, i.e. the model doesn't catch enough features, more regularization will lead to over-fitting, i.e. the model catch noise in the training set that is also bad for our model. In
the middle the complexity of our model is good, this is a trade-off between catching more features and less noise.
以下是我的cs224d github的地址,有想参考的朋友可以参考。不过写的不太好,别喷我。
https://github.com/NeighborhoodWang/CS224D-problem-set/tree/master/Psets/Pset1/assignment1
写程序的时候遇到几个问题,记录下来:
1.在python里喜欢把向量表示成一行的形式,这让我使用惯了matlab的人有点不习惯
2.把一个矩阵或者向量赋给其他变量的时候得使用x.copy()的方式,否则的话只是赋过去它的指针
3.gradient check的时候要用精度高的也就是两边都得减去eplison的那个(这个整死我了)
http://blog.csdn.net/neighborhoodguo/article/details/47071597
1.assignment1里的计算题的详细推导过程
编程题里的negative sampling和第三题(a)的推导过程类似,所以就没有重新推导了4.(a)Because over-fitting will make out model have a poor generalized error and overfit the training set. In order to improve our model's accuracy, we should introduce regularization to avoid over-fitting.
(b)That is a "v" curve shape, since less regularization will lead to under-fitting, i.e. the model doesn't catch enough features, more regularization will lead to over-fitting, i.e. the model catch noise in the training set that is also bad for our model. In
the middle the complexity of our model is good, this is a trade-off between catching more features and less noise.
2.程序github
以下是我的cs224d github的地址,有想参考的朋友可以参考。不过写的不太好,别喷我。https://github.com/NeighborhoodWang/CS224D-problem-set/tree/master/Psets/Pset1/assignment1
写程序的时候遇到几个问题,记录下来:
1.在python里喜欢把向量表示成一行的形式,这让我使用惯了matlab的人有点不习惯
2.把一个矩阵或者向量赋给其他变量的时候得使用x.copy()的方式,否则的话只是赋过去它的指针
3.gradient check的时候要用精度高的也就是两边都得减去eplison的那个(这个整死我了)
相关文章推荐
- 动态代理
- 如何查看自己电脑上windows installer的版本?
- logstash 1.5.3 配置使用redis做续传
- 强大的ViewDragHelper和ViewDragHelper的妙用 一
- Android 中Service 和Activity之间传值。(涉及BroadCast的基本用法)
- 内存实验相关分析(7.23)
- Maven 使用 二——nexus
- 设计模式—生产者消费者模式
- Scala课程01
- Instruments模板介绍(更新中...)
- springboot 整合apache shiro
- Github 访问时出现Permission denied (public key)
- 【Powershell】【静态数组】 数组的使用(一)
- 用互联网为中国制造抢回失去的十年
- 欢迎使用CSDN-markdown编辑器
- javascript 毫秒转日期 日期时间转毫秒
- C/C++ memmove 和 memcpy
- IT程序员及相关领域的好书推荐
- OpenGL教程翻译 第六课 平移变换
- Android之——AIDL小结