|
|
|
|||||||
| FlashChat | Actuarial Discussion | Preliminary Exams | CAS/SOA Exams | Cyberchat | Around the World | Suggestions |
DW Simpson |
Actuarial Salary Surveys |
Actuarial Meeting Schedule |
Contact DW Simpson |
 |
|
|
Thread Tools | Search this Thread | Display Modes |
|
#21
11-02-2017, 03:59 PM
|
||||
|
||||
(To nobody's surprise) Alpha Go has been upgraded a bunch. The latest version went 100:0 against the version that we were talking about last year.
AlphaGo Fa 5:0 against Fan Hui AlphaGo Lee 4:1 against Lee Sedol AlphaGo Master 60:0 against professional players; AlphaGo Zero 100:0 against AlphaGo Lee,89:11 against AlphaGo Master One of the more interesting aspects is the latest version wasn't trained on human games at all. They were slowing it down. It is entirely self-taught. Also the speed of its progress was pretty scary. It only took 3 days of training to beat the old version. 40 days to mature.
__________________
Sredni Vashtar went forth, His thoughts were red thoughts and his teeth were white. His enemies called for peace, but he brought them death. Sredni Vashtar the Beautiful. Last edited by Sredni Vashtar; 11-02-2017 at 04:10 PM.. 
|
|
| Thread Tools | Search this Thread |
| Display Modes | |
|
|
Linear Mode
