bug-gnubg
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Bug-gnubg] Neural Net Tutorials


From: Ralph Moritz
Subject: Re: [Bug-gnubg] Neural Net Tutorials
Date: Fri, 6 Mar 2009 19:15:31 +0200

I did some calculus at school, but that was years ago. I haven't studied either of the other two though. I'm willing to do some learning if these subjects are prerequisites for a good understanding of neural networks.

2009/3/6 Øystein Johansen (OJOHANS) <address@hidden>
Welcome to a really interesting world of backgammon, neural networks, machine learning and AI.

It makes it simpler to explain if you tell us a bit about your mathematical background. What do you know about linear algebra, calculus and statistics? Have you studied any of these subjects?

-Øystein


>-----Original Message-----
>From: bug-gnubg-bounces+ojohans=statoilhydro.com@gnu.org
>[mailto:bug-gnubg-bounces+ojohans=statoilhydro.com@gnu.org] On
>Behalf Of Ralph Moritz
>Sent: Friday, March 06, 2009 2:24 PM
>To: address@hidden
>Subject: [Bug-gnubg] Neural Net Tutorials
>
>Hi,
>
>I want to learn about neural nets and how gnubg uses them to
>learn to play better backgammon. I've read Tesauro's paper
>"Temporal Difference Learning and TD-Gammon" and this gave me
>some insight. Specifically, this was my first time reading
>about TD learning, MLPs etc.
>
>I understand that machine learning is a vast subject that
>requires years of study to properly appreciate, so I guess
>what I'm looking for is more of a practical introduction on
>how to implement a neural net for some practical purpose. I've
>googled for neural net tutorials but come up empty handed. I
>know reading the code is one option, but I'd prefer to do this
>_after_ I've learnt the basics. Could someone on this list be
>so kind as to point me in the right direction? Any information
>that is easy for a layman to digest would be much appreciated.


-------------------------------------------------------------------
The information contained in this message may be CONFIDENTIAL and is
intended for the addressee only. Any unauthorised use, dissemination of the
information or copying of this message is prohibited. If you are not the
addressee, please notify the sender immediately by return e-mail and delete
this message.
Thank you.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]