MangoLiu / mangoliu.github.io
MangoLiu's Bolg
☆53Updated 8 years ago
Related projects: ⓘ
- sparse word2vec☆109Updated 2 years ago
- A recommend system forked from APEX☆82Updated 10 years ago
- 《统计学习方法》的读书笔记,重现了大部分的课后题,仅供参考。☆68Updated 6 years ago
- a parameter server for distributed machine learning applications☆105Updated 8 years ago
- In online advertising, click-through rate (CTR) is a very important metric for evaluating ad performance. As a result, click prediction s…☆33Updated 5 years ago
- ☆142Updated 8 years ago
- 2016CCF-sougou-code&PPT☆55Updated 7 years ago
- LR、FM model solved by ftrl and sgd parallel on MPI☆111Updated 6 years ago
- ☆22Updated this week
- 算法相关的各种论文和slides☆42Updated 5 years ago
- Multi-thread implementation of Factorization Machines with FTRL for multi-class classification problem which uses softmax as hypothesis.☆70Updated 3 years ago
- ☆57Updated this week
- ☆50Updated this week
- Some articles written by Bao Jie☆0Updated 7 years ago
- ☆93Updated 2 years ago
- ☆27Updated 6 years ago
- this is my presentaion area .个人演讲稿展示区,主要展示一些平时的个人演讲稿或者心得之类的,☆57Updated 4 years ago
- logistic regression model by ftrl based on ps-lite(parameter server)☆33Updated 8 years ago
- xlearn 中文文档☆18Updated 2 years ago
- 京东JData算法大赛-高潜用户购买意向预测☆18Updated 7 years ago
- MXNet for CTR☆50Updated 7 years ago
- ☆52Updated 8 years ago
- A SimRank algorithm implementation using Spark☆49Updated 10 years ago
- 7th in a competition organised by ICT☆24Updated 8 years ago
- Using gbdt+lr in recommend system and comparing the auc of lr, gbdt, gbdt+lr.☆24Updated 7 years ago
- News recommendation system based on spark.☆47Updated 7 years ago
- Notes on Logistic Regression and OWLQN☆26Updated 7 years ago
- 通过对于现有开源分布式机器学习工具的整合(主要是基于参数服务器的logistic regression,xgboost,FFM,FM ),打造一个工业级的,可以线上使用的点击率预估流水线☆26Updated 7 years ago
- Chinese Tokenizer; New words Finder. 中文三段式机械分词算法; 未登录新词发现算法☆95Updated 7 years ago
- code exercise: dbscan(ballTree improve) | ctr(ftrl) | text classification(bayes..) | kmeans | general LR |..☆26Updated 8 years ago