Timeline for How to represent target variable for chess AI
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 28, 2016 at 10:30 | answer | added | Rolf Schorpion | timeline score: 1 | |
| Jul 27, 2016 at 22:37 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jun 30, 2016 at 18:21 | comment | added | Ryan Zotti | Yeah, they're useful when spatial closeness is important. For example, a pawn on a square next to a queen | |
| Jun 30, 2016 at 17:19 | comment | added | Ricardo Cruz | I was surprised to see "convolutional neural networks" in your list. These neural networks were made for image classification, and I know they have been extended for things like text. But I see wikipedia says they have been used for Go. Impressive stuff! | |
| Jun 27, 2016 at 21:15 | comment | added | Ryan Zotti | That's my question -- how I should shape my target data. Each record will be a single move. | |
| Jun 27, 2016 at 21:08 | comment | added | JeremyFromEarth | What is the shape of your data? How are you representing a game or a single step in a game? | |
| Jun 27, 2016 at 20:20 | answer | added | Alex R. | timeline score: 1 | |
| Jun 26, 2016 at 19:33 | history | edited | Ryan Zotti | CC BY-SA 3.0 |
added 286 characters in body
|
| Jun 26, 2016 at 18:20 | history | asked | Ryan Zotti | CC BY-SA 3.0 |