Coder Social home page Coder Social logo

nlp-love / ml-nlp Goto Github PK

View Code? Open in Web Editor NEW
15.2K 15.2K 4.5K 11.68 MB

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Home Page: http://mantchs.com/

Python 8.88% Jupyter Notebook 91.02% Shell 0.10%
deep-learning machine-learning nlp

ml-nlp's People

Contributors

nlp-love avatar tolicwang avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

mantchs ygbm anxiang1836 veikin zjaiaj taobot007 012huang wangzhonglei chuckwoody fresh-meet ddyuewang jinghu-ut lzchuan kakack xuzhipenganhui xuemingdi evvil franklinma810 xiaofangxiansheng2 zuanxian luye-huang ztl-35 sharejing tiansong1991 hellohktk zcr5959 shawngao94 guantianhua cgy1992 skywj tempestwk1 xiaxuer intohole lxgithub24 fansa piggyjam zwbjtu123 janussa wy2609 jiamim guo0842109 michaelwty fatflower youngooo legendtianjin easyfmxu allensmile smuzyg liyangrose xxyy1 hitdong kjq2019 guangtouwangba mysanantonio feuerwerk99 kkwellbbetter emmacirl typanda phrmgb yaoyaozhi carolinewinter88 zsirs nealzh tchigher lhhriver jhy616415267 zhangxiang02 xiaonanbi anfrankeinstein lwaekfjlk hhy5277 shaunstanislauslau yiguanxian rahuljyala7 songxianjin ligua czzlegend randyfhp jiaya12 alizer sunweiconfidence yushu-liu ethanlee555 jinjim lw19951231 mengxzh15 yak0xff lovebingo chutianba 761127457 ethpony newdee zyle0 wangdongya tianyikenan ai-related communicateconnectcreate timehsw thlo7777 awesome-archive

ml-nlp's Issues

频率派vs贝叶斯派、先验概率、后验概率这里概念有问题

老兄，频率派vs贝叶斯派、先验概率、后验概率这里概念有些问题呀
频率派和贝叶斯派主要区别在于对概率概念的定义，频率派用的客观概率，贝叶斯派用的主观概率
先验概率和后验概率区别在于多个随机变量信息的相互校验啊

GBDT data

GBDT训练数据和测试数据是一样的，可以更正下

seq2seq章节的一个修改建议

在seq2seq章节中的编码器小节中，输⼊ xt 的特征向量 xt 和上个时间步的隐藏状态..., 建议将其修改为`输⼊数据x^t和上个时间步的隐藏状态，因为在编码器中每个隐藏层的输入是输入数据和上一步的隐藏状态，而不是输入数据的特征向量。

GBDT不需要对特征进行归一化

GBDT由于是采用树模型作为基模型，因此也不需要对特征进行归一化。GBDT的求导是针对前面模型的预测值进行求导的而不是针对参数进行求导的，因此从梯度角度考虑也并不需要对特征进行归一化。

GBDT和RF算法的对比存在问题

第3章说GBDT使用了决策树，不需要归一化等特殊处理，后面对比RF时又说GBDT需要归一化，二者矛盾，希望作者您查看是否存在描述错误，有的话进行订正。

感谢您的工作！祝好！

**

文章中的**是什么啊？

kc_train2.csv

housing price 中没有提供数据kc_train2.csv

target=pd.read_csv('kc_train2.csv') #销售价格

运行预处理数据代码的时候报错

print(globals()['doc'] % locals())
TypeError: unsupported operand type(s) for %: 'NoneType' and 'dict'

请问在word2vec.ipynb这个样例中遇到这种情况应该该怎么办

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.