| |
Hermit
Registered: May 2008
Posts: 208 |
AI on C64
Were there any Artifical Intelligence experiments on C64?
-A neuron is not really more than a body which sums more weighted inputs into an output..(in real life sigma-sum)
-A neural network appears when these are connected to each other, in most cases by careful arrangement.
-The neurons can learn by modifying their (originally randomized) input-weights to reach the wished (reference) value at their output.
-The learning process takes some iterations depending on the strength (multiplier) of the feedback of actual error delta (wished reference for actual inputs -minus- the actual output). The optimal multiplier seems between 0.2..0.3 from my experiments.
A neuron's pins, datas (weights) and connections can be modelled in assembly easily. A byte can be a value of input-weight, and the weighted inputs can be added (and divided) together to a byte, which will represent the output of the neuron when the neuron was simulated once in a step. Then a connection list can route this output to other neuron's input.
See my example on my homepage (neuron-DAC2.xls).
http://hermitsoft.uw.hu/pcprog/pcprog.html
It's an Excel file that shows iterations and learning curve of a Neuron. We teach it to be a special Neuron - be it a DAC (Digital-to-Analog converter).
After several iterations the error gets smaller-and-smaller, then our Neuron learns to be a DAC, the needed information is 'stored' in its weights.
No concept yet, but C64 may be able to simulate simple neural networks at 1MHz, which could be useful in games, and even in demos, or who knows, even in 'random' composing for music editors..
Maybe you're interested..maybe not.
Have a good exploration.
Hermit Software Hungary |
|
| |
AlexC
Registered: Jan 2008
Posts: 299 |
Well, never really thought about it before but I guess that the use on c64 is somehow limited. First of all all action games with sprite multiplexing, msx and chains of irq routines can leave no space for advance AI or allow AI to be invoked only in certain screen lines. A lot of games have some spare time but it all comes to design.
The only use in terms of games I can imagine right away are chess-like games and strategy ones. Actually it would be interesting to look into Final Chesscard because this could be the game which uses similar approach. After all the additional CPU must have some use... |
| |
Zyron
Registered: Jan 2002
Posts: 2381 |
I believe Eliza was supposed to have some sort of AI, not a total success though. |
| |
Kickback
Registered: Apr 2004
Posts: 97 |
Quote: I believe Eliza was supposed to have some sort of AI, not a total success though.
LOL!!!! Eliza.... "How do you feel today.." Man that brings back some memories! |
| |
Spinball
Registered: Sep 2002
Posts: 88 |
the coder of this game at least says it is using AI:
http://noname.c64.org/csdb/search/?seinsel=all&search=kitron&Go.. |
| |
Frantic
Registered: Mar 2003
Posts: 1648 |
I have done some stuff using GP ("Genetic Programming") on the C64. All of it unreleased so far though. One of those productions may actually be finished in a not too distant future (or not).
(A not very important sidenote: Brain activity is not completely reducible to firing patterns, to be precise. You also have, according to some, gamma-waves, and stuff like that.. Anyway, this is not of high relevance for the issue of implementing some sort of AI on the C64 of course... :) |
| |
enthusi
Registered: May 2004
Posts: 677 |
Actually I think most (all?) C64 games do well with pseudo AI.
As in a set of rules that interact which each other to create complexity.
Not Even Human - Inhumane Edition
Does that and despite the fact that it had to be rather limited due to rastertime I was quite happy with the result.
A few more extra functions and it would be better than any real, theoretically satisfying AI I think... |
| |
Hermit
Registered: May 2008
Posts: 208 |
Hi Mates
I tried Eliza, it seems a cleverly programmed thing.
Though in my opinion, the good approach to AI is the Neuron-based AI.
The difference between the 'pre-programmed' and Neuron-based
AI is the learning power. And the Neurons are working truly paralell not in serial after each other..so with today's serially working computers the Neuron models aren't working as fast as the ones realized on e.g. paralell-working FPGAs..
The researches which try modelling AI with Neurons is to be improved a lot as the laboratories couldn't reach that much number of neurons (on FPGAs, etc) with that much connections as even the simplest brains..they reached the complexity of worms or bugs (do not laugh, please :)
So I'm far from trying to modell AI on brain's level, that programs try (as e.g. Eliza). Instead the well constructed neural networks could solve a lot of problems after learning. The learning is what 'programmed' AI solutions are mainly missing, and I think they'll be less used in the future.
Some good examples can be found on net about what today's neural networks can solve..e.g. speech recognition, finding out the language-type from source code, decide if an applicant is good for a job, etc..
On C64 at 1MHz processor speed only limited numbers of neurons can be modelled, but if there's a good construction in their connection, they can solve problems after learning phase, that none of the 'pre-programmed' AI programs can solve..and this need much less system resources than using predefined values for decisions..
To make my (maybe complicated) explanation clearer, I'll show some links that could point what I'm saying with preferring neural networks.
http://en.wikipedia.org/wiki/Neural_network
http://portal.acm.org/citation.cfm?id=206913.206999
http://cslu.cse.ogi.edu/tutordemos/nnet_recog/recog.html
http://www.neuralnetworks.it/neuralsignature.asp
http://www.advancedsourcecode.com/netassembler.asp
etc,etc, I think the Neural modelling of biology is the future in AI..
Hermit Software Hungary |
| |
Wile Coyote
Account closed
Registered: Mar 2004
Posts: 646 |
I have always assumed Chess games have a level of AI, as they take some time to make their moves, at least on 8-bit machines.
The whole AI thing is interesting. |
| |
enthusi
Registered: May 2004
Posts: 677 |
"AI" is very ill defined, at least not used very precisely.
Chess games usually dont have AI as it was mentioned here.
Same with practically all games so far.
Not 'learning' the proper way.
Check out connect-4-games. You will never win against a good one, yet it has ONE rule how to play only.
I remember this whole discussion when Command&Conquer came out. I friend of mine wrote part of his thesis about the 'AI' of the Harvester, hehe. |
| |
Martin Piper
Registered: Nov 2007
Posts: 722 |
Regarding AI and learning. The robots in Berzerk Redux have a little bit of AI, they try to avoid walking into walls and will look for a direction around a wall if they are blocked.
Simple enough of course.
Regarding learning:
One idea I did have was to note which areas of the screen robots were killed. Then the remaining robots would prefer to avoid those areas. I never did put it in though as there are not that many robots on each screen to make it a worthwhile check. |
... 14 posts hidden. Click here to view all posts....
|
| Previous - 1 | 2 | 3 - Next |
