issue133:c_c
Différences
Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentesRévision précédente | |||
issue133:c_c [2018/05/31 14:12] – andre_domenech | issue133:c_c [2018/05/31 15:34] (Version actuelle) – d52fr | ||
---|---|---|---|
Ligne 70: | Ligne 70: | ||
**Both of these AIs use something called deep learning - this is a step further from machine learning. While machine learning is dedicated to teaching systems to recognize specific patterns or accomplish specific tasks, deep learning is more abstract. Take AlphaGo for example - it was taught the rules of Go and was fed basic data from a few Go records. However, it then began playing against itself and learning from those encounters. As such, it didn’t have a specific goal in mind (beyond “play Go”). This application of pitting two versions of the system against each other helped AlphaGo learn the uncommon strategies it employed against Go professionals.** | **Both of these AIs use something called deep learning - this is a step further from machine learning. While machine learning is dedicated to teaching systems to recognize specific patterns or accomplish specific tasks, deep learning is more abstract. Take AlphaGo for example - it was taught the rules of Go and was fed basic data from a few Go records. However, it then began playing against itself and learning from those encounters. As such, it didn’t have a specific goal in mind (beyond “play Go”). This application of pitting two versions of the system against each other helped AlphaGo learn the uncommon strategies it employed against Go professionals.** | ||
- | Ces deux types d'IA utilisent ce qu'on appelle l' | + | Ces deux types d'IA utilisent ce qu'on appelle l' |
issue133/c_c.1527768765.txt.gz · Dernière modification : 2018/05/31 14:12 de andre_domenech