Applied Data Science
medium.com/applied-data-science · Group blog · on HN since 2017
A Medium publication on applied data science, with tutorials on AlphaZero, reinforcement learning, chess statistics, and XGBoost interpretability.
What HN saysHN commenters link it as an explainer for how AlphaZero and AlphaGo Zero work, plus its chess openings analysis and an AlphaZero tutorial.
15HN people shared it
6linked it in comments
42stories submitted
415story points
3 years agolast shared
2017people per year2026
Most-shared posts
- 1How to build your own AlphaZero AI using Python and Keras4 people · 97 points · first shared 2018 · 7 comments on HN
- 2How AlphaGo Zero works, explained in one diagram4 people · 10 points · first shared 2017 · discussion on HN
- 3Hallucinogenic Deep Reinforcement Learning Using Python and Keras3 people · 11 points · first shared 2018 · discussion on HN
- 4The Google 'Vs' Trick3 people · 7 points · first shared 2020 · 1 comments on HN
- 5How to Calculate the Trappiest Openings in Chess Using Stats2 people · 81 points · first shared 2021 · 26 comments on HN
- 6NEW R package: The XGBoost Explainer – make xgboost models fully interpretable2 people · 6 points · first shared 2017 · discussion on HN
- 7Analyzing the Facebook ads placed by the US presidential candidates1 people · 139 points · first shared 2019 · 35 comments on HN
- 8Remember AlphaZero? DeepMind have now released MuZero. Here's how it's different1 people · 18 points · first shared 2019 · discussion on HN
- 9How to Build Your Own AI To Play Any Board Game1 people · 6 points · first shared 2021 · discussion on HN
- 10Pele – The Data Driven Football Commentator1 people · 5 points · first shared 2019 · discussion on HN
- 11The 5 Rules of Product-Driven Data Science1 people · 4 points · first shared 2019 · discussion on HN
- 1220,465 Chess Games Drawn Using Graph Networks1 people · 4 points · first shared 2020 · discussion on HN
- 13The November 2019 UK Election Cyberattack In One Chart1 people · 4 points · first shared 2019 · discussion on HN
- 1424 data science projects that will transform your business1 people · 3 points · first shared 2017 · discussion on HN
- 15Coronavirus vs. 105 Years of Deaths Data1 people · 3 points · first shared 2020 · discussion on HN
What HN people wrote when they linked it
rprenger · 2024-02-08
This is pretty close to how AlphaZero works.
https://medium.com/applied-data-science/alphago-zero-explained-in-one-…
MauranKilom · 2021-12-02
Here is someone doing that on a non-GM level: https://medium.com/applied-data-science/how-to-calculate-the-trappiest…
Erlich_Bachman · 2018-04-20
> last time I caught a ball in a similar situation I moved like this, so let me start with that and correct based on visuals, audio, proprioception, and cognition
There are types of neural networks (and other algorithms) that work literally like that. Just because a simple deep perceptron does not work like that does not mean no network does.
This one is just off the top of my head, it's quite recent but the memory part is based on old prior work.
https://medium.com/applied-data-science/how-to-build-your-own-world-mo…
UPD: without even digging deep in the different types of networks, even AlphaGo(/Zero) works like that.
chrisfosterelli · 2018-01-26
The link looks https to me, but this is where it redirects if that's of any use: https://medium.com/applied-data-science/how-to-build-your-own-alphazer…
anfractuosity · 2018-01-26