Data Science Archive - TELEGRAM CHANNEL

Updated:

 
1,912

 (0)

Data Science Archive is a popular Telegram Channel with 1,912 members. There are no reviews yet for this channel.

Channel 'Data Science Archive' focuses on data management, data formats & protocols, social sciences, economics, political science and you may subscribe to this channel by clicking the "Open" button (opens in Telegram App).

Explore channel insights and genuine user reviews for 'Data Science Archive' channel below.

Data Science Archive CHANNEL WIDGET


Free widget which you can place on your website to show your channel details.
1912 SUBSCRIBERS Get Code
How to embed the code: Click on 'Get Code' and copy + paste the HTML code shown into your website.

Data Science Archive CHANNEL DESCRIPTION


Owner Description

小熊猫的个人工具收纳箱,还包括一些零碎的笔记,大概会有这些:

* 有趣/有价值/SOTA的会议论文和代码分享
* 自然语言处理,计算机视觉,语音信号领域进展
* Kaggle 和其他算法竞赛经验
* 反作弊,搜索和个性化推荐算法产品的工程化
* 统计学习,矩阵计算,贝叶斯相关的工具
* 可视化、算法服务相关的存储、并行和分布式计算工具

希望我收集的信息也可以帮到你,如果有其他建议,或者寻找工作机会,都可以给我发邮件: [email protected]

Data Science Archive channel is growing at a rate of 0% and has a potential to reach 2294 people. Advertisers can reach out to the channel admin for any advertising opportunities within this channel.

advertise with tdirectory

HOW TO SUBSCRIBE TO Data Science Archive CHANNEL?


You can join Data Science Archive by clicking the Open button on top, which will open up the Telegram channel page in the browser or in the Mobile App. Now review the details and click on JOIN CHANNEL. If it is a private channel, an admin has to review and approve your request, otherwise you will get immediate access to the channel.

advertise with tdirectory
1912
Channel Members
2294
Average Post Reach
0%
Channel Growth
-1.0
Rating Index

Data Science Archive MOST VIEWED POST


@DataScienceArchive : 最近针对时间序列拆解重新理解的时候发现对 additive model 理解仍然有一些偏差。发现通用解法中用b-样条基函数的有点绕,终于在看了pyGAM这个包的源码和文档中完全搞懂,不过平滑约束的程度很难有点难顶就是了。https://github.com/dswah/pyGAM
Posted on 2020-03-31 13:50:03 | Viewed 7583 times

Data Science Archive CHANNEL PREVIEW


@DataScienceArchive : 最近在上线前彻查API,不少收获来自内部也是开放的指南。https://github.com/microsoft/api-guidelines/blob/vNext/Guidelines.md

Posted on 2020-08-12 01:59:11 | 3036 views


@DataScienceArchive : 意外发现一篇特别好的频率派和贝叶斯派的博文:http://jakevdp.github.io/blog/2014/03/11/frequentism-and-bayesianism-a-practical-intro/

Posted on 2020-04-14 01:02:45 | 6918 views


@DataScienceArchive : 最近针对时间序列拆解重新理解的时候发现对 additive model 理解仍然有一些偏差。发现通用解法中用b-样条基函数的有点绕,终于在看了pyGAM这个包的源码和文档中完全搞懂,不过平滑约束的程度很难有点难顶就是了。https://github.com/dswah/pyGAM

Posted on 2020-03-31 13:50:03 | 7583 views


@DataScienceArchive : 最近重新开始接触时间序列,找到一个蛮不错的基础教材,准备开始恶补。http://www.math.pku.edu.cn/teachers/lidf/course/atsa/atsanotes/html/_atsanotes/index.html

Posted on 2020-03-23 03:48:26 | 5722 views


@DataScienceArchive : 本来以为是个水货,结果刚点进去就发现了Pharebank 这个好东西,强烈推荐给有协作需求的在读 PhD。https://www.annaclemens.com/blog/16-free-tools-scientists-write-better-more-productively

Posted on 2020-03-07 17:16:27 | 5820 views


@DataScienceArchive : 关于 Tabular dataset 中 GBM 的一些意见,虽说是目前为止(或者未来的一段时间)应该还将继续是 STOA,但是或多或少会有一些用浅层 NN 融合的方案来继续提升性能,比较重要的一份参考是两年前的 https://www.kaggle.com/c/porto-seguro-safe-driver-prediction/discussion/44629 来源一条CPMP 的推文以及讨论:https://twitter.com/JFPuget/status/1233379034425384960

Posted on 2020-02-29 05:51:10 | 5513 views


@DataScienceArchive : CUDA 层面重新实现的几种 RNN,自带Zoneout 和DropConnect,试用了一下 Py 和 C++的 API,确实是快非常多,API 可设定的参数还不是太多。https://github.com/lmnt-com/haste

Posted on 2020-02-26 02:54:53 | 4607 views


@DataScienceArchive : 来自 Huggingface 的 tokenizer,Rust 实现,确实速度惊人。https://github.com/huggingface/tokenizers

Posted on 2020-01-14 07:52:50 | 4700 views


@DataScienceArchive : HuggingFace Transformers 包加了几组中文的 pre-trained models,包括 BERT-wwm, RoBERTa-wwm, XLNet,来自哈工大和讯飞。https://github.com/ymcui/Chinese-BERT-wwm/blob/master/README_EN.md

Posted on 2019-12-23 08:32:55 | 4873 views


@DataScienceArchive : 2019 ACL Salesforce Research 上常识阅读理解paper 的 code 更新,依赖 huggingface 的 transformers,看过 demo 还是非常不错的。https://github.com/salesforce/cos-e

Posted on 2019-12-21 07:36:40 | 4501 views


Data Science Archive ANALYTICS


Channel analytics based on historical data.

Community Index

Rating Index

Aggregated Rating

Data Science Archive CHANNEL REVIEWS (0)


Not yet reviewed. Be the first to review "Data Science Archive" channel.

Own this channel? Contact us to know how you can efficiently manage subscribers, how to market your channel, view indepth analytics and much more...

SUBMIT TO TELEGRAM DIRECTORY

NOW YOU CAN SUBMIT YOUR TELEGRAM CHANNELS AND GROUPS TO TELEGRAM DIRECTORY!

Some reasons why you should add your Channels, Groups and Bots to Telegram Directory, the largest online catalogue of Telegram resources.

Visibility

Your channel or group gets more visibility and thus more members and subscribers

Analytics

With advanced analytics, you get better understanding of your audience and growth

Feedback

Get direct feedback from your users, monitor the reviews and keep the user base intact

SEO

Your channel or group gets a dedicated page which gets indexed by the search engines