Subject:
|
AI
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Sun, 17 Oct 1999 02:49:21 GMT
|
Original-From:
|
ts <ts@zylotech.=SayNoToSpam=com.au>
|
Viewed:
|
476 times
|
| |
|
|
Can we make these things learn?
I'm no expert on AI or nothing, but perhaps by making, for example, program 1
write program 2, write to program 3 etc, and use a some kind of a genetic
algorithm to determine best output. Or would all this be infeasible with the RCX
unit?
Also, what kind of space do we have for our programs? Can we concatenate
programs to make bigger ones?
Tony
--
MIME ATTACHMENTS DISCARDED:
1. Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Content-Length: 959
|
|
Message has 1 Reply:
 | | Re: AI
|
| Tony- AI is a huge field, encompassing a variety of algorithms and techniques. Some of them will work OK on the RCX, others take just too much computation, especially when floating point is required. Also, when you talk about functions and all that, (...) (25 years ago, 18-Oct-99, to lugnet.robotics)
|
16 Messages in This Thread:
  
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
