Mike, Thanks for explaining your experimental setup in more detail. I think I've got a better handle on it now. :) I still have a few questions though. ... So...
Derek, Cheers for the feedback, I'll start by answering your questions. ... Yes. I use -1.0 for invalid (for ex. no mouse sighted) and 0.0 to +1.0 for valid...
... <snip> ... Okay, gotcha. However, this set of inputs seems like it might be a little redundant. The cat is also receiving input on its absolute position...
... <snip> ... I think these inputs will be necessary for the situations when the cat has not seen the mouse yet and has no idea where to look. This could be...
Could you separate the problem code and make it available so that I or someone else might have a go at the same problem? Using your code is the only way to be...
Mitchell, When the project is wrapped up (first week in May) I will be making everything freely available: dissertation and source. Until then I'm just gonna...
Well, I was on a roll there for a bit but now I'm back to hitting my head on the brick wall (much like my cat). My initial goal was to evolve 5 behaviours: 1)...
I'm not sure how familiar people are with this domain. I picked up on it last year from a post on the Genetic Programming yahoo group, it's basically 6 inputs,...
... Ken, I am going to give this approach a shot now but have a couple of questions for you. 1) Would you suggest that I do the normal NEAT start with just...
Hi,
This sounds like an excellent result.
At 23:28 03/04/2005, you wrote:
>I'm not sure how familiar people are with this domain. I picked up on it
>last...
... Yeh. It would be interesting to run the search in pruning mode to trim away the 'chaff', thus revealing the functional parts of the champion network for...
Hi Mike, ... population ... inputs ... Yes, that's right, that is reccurent and it's what I'm suggesting. My idea is this: If the task is so memory-dependant...
... ... and the fitness is assigned as the closeness to the expected output, 1.0 for spot on, 0.0 assigned for completely wrong. Total score is thus however...
At 21:21 06/04/2005, you wrote:
>Ian Badcoe wrote:
>
> >Hi,
> >
> >This sounds like an excellent result.
> >
> >
> >
>Yeh. It would be interesting to run the...
... The type of approach you suggest did cross my mind momentarily, but I didn't give them any thought because past experience suggests taking shortcuts gives...
Depends a little bit on what you are aiming at: do you mean taking a taught course, doing a PhD or getting hired as a lecturer? Or do you mean the private...
Yes, it is possible. In fact we've done XOR runs before where the starting topology is completely disconnected (i.e., 0 connections) and it is able to find a...
Thanks Julian, I guess I mean in the public or private sector job wise. Like working for company X or government organization Y. Rog ... Yahoo! Mail Stay...
EvSail-2.5 has been released. It's a free download from http://sourceforge.net/projects/annevolve. EvSail is a program that uses neuroevolution to obtain an...
Hi Rog, one thing I'd say is it that it certainly would help to have educational background in those areas. Since neural nets and gas are largely considered...
... and ... of ... Thanks for your reply, Phillip. As a practical matter, is setting all connections to zero (including input connections) somthing that I set...
Hi, This is the other half of the ANJI team. I believe if you just set the following two properties the following ways: initial.topology.fully.connected=false ...
As some of you know, I am currently a post-doc but I have been searching for a permanent position for quite some time now. I have finally accepted a...
