BGonline.org Forums

Training a Neural Net (like GNUBG or XG)

Posted By: Jake Jacobs
Date: Tuesday, 27 April 2010, at 2:22 a.m.

In Response To: Training a Neural Net (like GNUBG or XG) (Daniel Murphy)

Just hearsay, but someone (might have been Magriel) told me, way back when Jelly and Snowie were first appearing on the scene, that neural nets could overtrain, and you had to freeze them before they regressed too much. Not sure if it is true - it is just hearsay. But I noticed that over the years Snowie seemed to add specialized modules rather than revamping the net itself.

Messages In This Thread

• Training a Neural Net (like GNUBG or XG)
  Jason Lee -- Tuesday, 27 April 2010, at 12:02 a.m.
  • Training a Neural Net (like GNUBG or XG)
    Daniel Murphy -- Tuesday, 27 April 2010, at 1:03 a.m.
    • Training a Neural Net (like GNUBG or XG)
      Jake Jacobs -- Tuesday, 27 April 2010, at 2:22 a.m.
      • Training a Neural Net (like GNUBG or XG)
        Ian Shaw -- Tuesday, 27 April 2010, at 6:28 a.m.
        • Training a Neural Net (like GNUBG or XG)
          Fabrice Liardet -- Tuesday, 27 April 2010, at 11:34 a.m.