|
An improved code project article search engine.
Jason Henderson My articles
"The best argument against democracy is a five-minute conversation with the average voter." - Winston Churchill
|
|
|
|
|
Good idea, but not for our main project.
"Do unto others as you would have them do unto you." - Jesus
"An eye for an eye only makes the whole world blind." - Mahatma Gandhi
|
|
|
|
|
This is something I'm working on. Essentially it's a DB thing and is probably no more than a weekend's worth of work for me to do properly. The trick is finding that weekend but rest assured it is top of mind.
cheers,
Chris Maunder
|
|
|
|
|
How about an artificial life project with a CP twist?
imagine Reproducing Bobs...
Seriously, would anyone be interested in an ALife/AI project?
This may satisfy JoeSox and also give the rest of us some AI experience.
Jason Henderson My articles
"The best argument against democracy is a five-minute conversation with the average voter." - Winston Churchill
|
|
|
|
|
Jason Henderson wrote:
This may satisfy JoeSox and also give the rest of us some AI experience.
I think it is definitely time for some AI articles here on CP, which I am planning on doing. I am currently planning an ALife demo, nothing fancy just a demo on using Jungian theory(which the AI community doesn't see the necessity of this, imo) to simulate conscious human thinking. It will probably just be a dialogbox app, I installed VS.Net Beta2 msdn edition to get familiar with C#. It's just a matter of finding the time.
I started a project at sourceforge
http://sourceforge.net/projects/humanaiproject/[^]
and plan to start "recruiting" people after I get approved with aaai.org.
But this project I want to be the real deal if I can't hook up with some professional group (university or MIT;P COG[^] needs my theories/ideas/approach )
Later,
JoeSox
www.humanaiproject.org
"Reality is merely an illusion, albeit a very persistent one."
-Albert Einstein (INTP)
|
|
|
|
|
JoeSox wrote:
I am currently planning an ALife demo, nothing fancy just a demo on using Jungian theory(which the AI community doesn't see the necessity of this, imo) to simulate conscious human thinking.
Interesting. I know very little about "Jungian theory" but I after doing a little research (Since your post). A couple of wild ideas have struck me in regards to the derived Myers-Briggs code.
eg there are 8 states, and 16 positions.
So we now have 2^7 combinations.
If we to consider that any of the 2^7 combinations could be in response to the last post and atates and attitudes of the respondent.
We would end up with 2^14 combinations. This logic could be stored in either a btree or a state - machine code. And would result in determining which of the 8 states to use in communication.
----
As in the analogy of telling a joke, the time really matters.
Well with an "anthromorphic" character, when, where and why it changes it's personality is of great importance to another form creating a relationship.
----
Regardz
Colin J Davies
* WARNING *
This could be addictive
The minion's version of "Catch ![Green Alien | [Alien]](https://codeproject.global.ssl.fastly.net/script/Forums/Images/alien.gif) "
It's a real shame that people as stupid as you can work out how to use a computer. said by Christian Graus in the Soapbox
|
|
|
|
|
Colin Davies wrote:
We would end up with 2^14 combinations. This logic could be stored in either a btree or a state - machine code. And would result in determining which of the 8 states to use in communication.
well, I haven't thought of it that way. The way my research is going, ideally, it makes sense to simulate neurotransmitters which in turn would effect Sensation,Intuition, thinking, and feeling. Which would result in simulating any of the 16 personalities.
I wrote a little intro to my ideas here[^].
why are you interested in the 8 states?
Later,
JoeSox
www.humanaiproject.org
"Reality is merely an illusion, albeit a very persistent one."
-Albert Einstein (INTP)
|
|
|
|
|
Okay, I have to be careful I don't confuse myself here. 
Any I hope we are on the same page.
The eight states (or functions) are the output, by means of facial expressions and bodylanguage and grammar used.
The 16 personalities, are used partially for determining which of the states the AI is in.
What I'm thinking about is having a consistent characterisation, so even if the AI's responses aren't great, the AI presents itself well.
Options for the AI would be how fast the states could change.
Any being going from ANGRY (Introverted Feeling) to Jocular extraverted intuition in a flash of the hat is likely to arouse suspicion.
IMHO: A good AI at emotional connections, would have the ability to use Neuro Liguistic Programming to detect the personality of who it was communicating with, thus it could then respond with a personality base similar to the user.
Regardz
Colin J Davies
* WARNING *
This could be addictive
The minion's version of "Catch "
It's a real shame that people as stupid as you can work out how to use a computer. said by Christian Graus in the Soapbox
|
|
|
|
|
Colin Davies wrote:
IMHO: A good AI at emotional connections, would have the ability to use Neuro Liguistic Programming to detect the personality of who it was communicating with, thus it could then respond with a personality base similar to the user.
When you speak of NLP, and so we are one the same page, do you mean this?
http://skepdic.com/neurolin.html[^]
if so NLP is more a form of Psychological therapy than anything else, and could be learned by my HAI
well, humans are learning machines. I am working on my HAI so that whatever it learns it will have the ability to do, just like real humans.
For example, if my HAI has learned and formed it's own concept of "anger", then it will respond according to it's own personality preferences(simulated neurotransmitters that run the Self(MBTI)) according to the current situation and environment(like if a person was yelling at the HAI for some reason). 
Later,
JoeSox
www.humanaiproject.org
"Reality is merely an illusion, albeit a very persistent one."
-Albert Einstein (INTP)
|
|
|
|
|
Joe, Skepdic.com as usually states some good clear truths.
-----
IMHO: 98% of the NLP stuff about is garbage, and is as useful as aromatherapy and cannibalism to become smarter.
However there in the early stages of the NLP philosophy there was a lot of sense made, but then it became a marketing scam.
-----
IMHO again:
Consider these cases
A man is attracted to a female, so he breaks the ice.
"Hi look I'm all alone here can I buy you a drink",
Response a.) "Sure, I'll have a white wine."
Response b.) "An orange juice would be loverly."
Response d.) "I could sure down a Bud now."
Okay now match up the man's next line setting.
"You wouldn't know anywhere in this town that I can get a radiator fixed"
"I see a new play is being shown the road at the theater ."
"This is a real charming place isn't it."
Easy huh,
But not only is what the mans topic different but, also the language type and structure he uses changes as well.
Consider the differnece in how you talk to a young child, and to your boss.
Regardz
Colin J Davies
* WARNING *
This could be addictive
The minion's version of "Catch "
It's a real shame that people as stupid as you can work out how to use a computer. said by Christian Graus in the Soapbox
|
|
|
|
|
Colin Davies wrote:
Consider the differnece in how you talk to a young child, and to your boss.
what you are talking about is context[^] and is developed in, my current opinion, is Intuition.
See my representational graph of my current thinking[^]?
Later,
JoeSox
www.humanaiproject.org
"Reality is merely an illusion, albeit a very persistent one."
-Albert Einstein (INTP)
|
|
|
|
|
JoeSox wrote:
See my representational graph of my current thinking[^]?
Maybe it's just the way my mind works but I find it easier to understand via cycles of process controls, rather than via representations. My belief is that the context generated is an output of the AI's state.
Your "Is emotion created decision" seems to have the same process for both "neutral" and "no".
Also wouldn't a direct link from "common sense" to "outputs" have a benefit.
And The "Nat Lang Proc" arrow go bidiretionally to "Thinking Logic"
??
In a few days I'll post a description of my "current thinking" about crating a AI form.
Every where you go thre are totally different philosophies on what AI is or how it should be implimented.
Regardz
Colin J Davies
* WARNING *
This could be addictive
The minion's version of "Catch "
It's a real shame that people as stupid as you can work out how to use a computer. said by Christian Graus in the Soapbox
|
|
|
|
|
Colin Davies wrote:
Your "Is emotion created decision" seems to have the same process for both "neutral" and "no".
I quickly threw that in there because research from the brain, if I remember correctly (I forgot to write down the reference on that one) says emotion is produced from perception, I think it is also produced by judgment, I have done so much reading I need to find my notes.
anyway feel free do down load my incomplete VC++ 6 demo
http://savemall.net/downloads/carl.zip[^]
I am not a professional coder so the code is not perfect.
It doesn't actually do anything now but read the comments in the code. I plan on adding three more editboxes to the dialog, Carls innerworld, carl's outerworld, and one to display administrator messages.
Later,
JoeSox
www.humanaiproject.org
"Dream as if you'll live forever; live as if you'll die tomorrow."
- James Dean(ISTP)
|
|
|
|
|
|
|
|
"the minion" himself/herself I guess.
Regardz
Colin J Davies
* WARNING *
This could be addictive
The minion's version of "Catch ![Green Alien | [Alien]](https://codeproject.freetls.fastly.net/script/Forums/Images/alien.gif) "
It's a real shame that people as stupid as you can work out how to use a computer. said by Christian Graus in the Soapbox
|
|
|
|
|
I actually tossed around the idea of a .NET engine that we could write plug-ins for, and which could battle each other and use primitive AI to attack, defend, build, repair and form clans. And then Microsoft built Terrarium 
cheers,
Chris Maunder
|
|
|
|
|
That would be a kick arse thing to do, even if MS did it already.
Jason Henderson My articles
"The best argument against democracy is a five-minute conversation with the average voter." - Winston Churchill
|
|
|
|
|
|
I personally think AI related is a great idea. In fact an Life sounds really cool to me.
With respect to the MS thing, something with the same goal, advancing the "language" is available. It deals with AI and learning a language.
http://robocode.alphaworks.ibm.com/home/home.html[^]
This has all source code available. Could be used, the logic that is, to create a framework for the ALife.
|
|
|
|
|
Rather than just an ALife/AI, how about an ALife/AI project that is a P2P system. No central servers. Possible research information:
http://www.jxta.org/[^]
|
|
|
|
|
I'm a graphics loving guy and I'd like to work on a fractal engine of some sort.
This may not have any practical use except for personal enjoyment.
Jason Henderson My articles
"The best argument against democracy is a five-minute conversation with the average voter." - Winston Churchill
|
|
|
|
|
I've worked on a project like that fro about 2 years I called it ChaosImager http://joelholdsworth.members.beeb.net/CI1/INDEX.HTM[^]. I found that the mainstay of my project was having good interface like BCG - and when that ceased to be free the project kinda lost momentum!! But if you look at other famous fractal makers such as UltraFractal they all have beutiful interfaces. So I think UGLY should be the first priority!!!
*¨¨`)
¸¸.·´ ¸.·*¨¨`)
(¸¸.·* ¸ .·*
¸¸.·*
(¸¸.~~> Joel Holdsworth.
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
![Rose | [Rose]](https://codeproject.freetls.fastly.net/script/Forums/Images/rose.gif)
disabled