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: OJOHANS
Subject: RE: [Bug-gnubg] Neural Net Tutorials
Date: Mon, 16 Mar 2009 14:56:34 +0100

[snip about linear algebra]
>> While you're at the library, try to find:
>> "Understanding Neural Networks And Fuzzy Logic", by Kartalopous, 
>> ISBN:8120316800
>>
>> It's small and well written, does not include hairy details, 
>and give a nice overview. (However, you need the basic linear 
>algebra). Tell me if you find this book and I can point out 
>the important chapters.
>
>Thanks. I'll try to find a book on & learn a little linear algebra.

Hi, Ralph!

Did you find some book on linear algebra?

Did you find Kartalopous?

Status?

>> Next question: Are you a coder? Do you code anything? Do you 
>want to learn coding? Any simple experience with any 
>programming language? Pascal in pre-school?
>
>No Pascal in pre-school, but I do write code for a living :) 
>I've read and written code in various incarnations of VB, 
>Delphi, Perl, C, C++ and C#. I don't claim to be an expert 
>though. In terms of algorithms & data structures, I know how 
>to implement the basic stuff like quick sort, binary search, 
>hash tables, linked lists, balanced binary search trees 
>(anderson, not the more complicated r/b trees) and simple 
>finite state machines.

Good! Really good! I assume I can talk about data types etc. The question in 
matter is converting the equations from the books to useful algorithms. 

Next questions: Have you ever coded any languages with matrix support (Matlab 
or Octave or Python w/numpy or anything similar? Or maybe C++ with a Matrix and 
Vector class and operator overloading). In that case we can start playing 
around with some code. Make your choice of programming language! If it's not 
supporting matrix types, you'll have to code a matrix times vector 
multiplication algorithm your self.

-Øystein


-------------------------------------------------------------------
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]