[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Cubeful equities: Janowski versus neural net

Posted By: Matt Ryder
Date: Wednesday, 6 January 2010, at 5:46 a.m.

I've been baffling my brain with an investigation of cubeful equities recently.

In the GNU manual, we found the following titbit:

"Evaluating the cubeful equity is much more difficult; it can either be estimated from the cubeless equity by using transformations as outlined by Rick Janowski or by constructing a neural net that directly outputs cubeful equities."

(Italicised emphasis mine.)

Has anybody experimented with the 'cubeful neural net' angle, given the somewhat imprecise nature of the Janowski formulae? It seems that GNU, Snowie and XG (plus BGBlitz?) all rely on Janowski.

Would this not be a fruitful avenue for future bot development?

(Note I'm not deriding Janowski's brilliant path-breaking work, but the current approach does have its profound limitations.)

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.