Virtual Humans Forum
Virtual Humans Forum
Home | Profile | Register | Active Topics | Members | Search | FAQ
Username:
Password:
Save Password
Forgot your Password?

Virtual Humans
Partner website:
Chatbots.org
 All Forums
 Virtual Humans
 Artificial Intelligence
 human mind map
 New Topic  Reply to Topic
 Printer Friendly
Next Page
Author Previous Topic Topic 
Page: of 25

toborman
Hooked Member



USA
289 Posts

Posted - Dec 10 2007 :  01:04:04  Show Profile  Visit toborman's Homepage
Jim, John, Grant, mikmoth

The following link will take you to a new site with a diagram of human mental functions and behaviors that might be the basis for AI engine functions. Suggestions, challenges, and commentary using this thread is appreciated.

http://mindmap.iwarp.com/

http://mindmap.iwarp.com

mikmoth
Moderator



USA
2082 Posts

Posted - Dec 10 2007 :  02:57:19  Show Profile  Visit mikmoth's Homepage  Reply with Quote
That is way neat... I like how one of the boxes says "Problem Solving"...

http://lhandslide.com
Go to Top of Page

GrantNZ
Dedicated Member



New Zealand
2677 Posts

Posted - Dec 10 2007 :  06:16:15  Show Profile  Reply with Quote
I had to grab a dictionary to understand the comments for "Refer"

It's a good map. A slightly depressing aspect is that any good AI should include routines (or capacity) for almost all those little boxes

This kind of diagram is a great organisational tool if you're coding an AI, kind of like a giant to-do list that also shows planned connections between areas of code. There would need to be more connections between some of the lower boxes, where methods and/or behaviours need more integration together. There would also need to be a great flexibility for change - projects like pioneering AI are very difficult to pre-plan with absolute accuracy!

Thanks toborman.
Go to Top of Page

hologenicman
Moderator



USA
3323 Posts

Posted - Dec 10 2007 :  06:40:38  Show Profile  Visit hologenicman's Homepage  Reply with Quote
Very nice layout for developing/testing an emerging AI.

I had trouble reading the print on my monitor for some reason which became frustrating, but from what I can read it is well thought out.

John L>
IA|AI

HologenicMan
John A. Latimer
http://www.UniversalHologenics.com

"If the Human brain were so simple that we could understand it,
we would be so simple that we couldn't..."
-Emerson M Pugh-

Current project:http://www.vrconsulting.it/vhf/topic.asp?TOPIC_ID=816&whichpage=1

DISCOVERY: The more I learn, the more I learn how little I know.
GOAL: There's strength in simplicity.
NOTE: Goal not always achieved.
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 10 2007 :  06:51:04  Show Profile  Visit toborman's Homepage  Reply with Quote
John

did you have trouble reading the download version?

http://mindmap.iwarp.com
Go to Top of Page

hologenicman
Moderator



USA
3323 Posts

Posted - Dec 10 2007 :  07:07:16  Show Profile  Visit hologenicman's Homepage  Reply with Quote
Actually, I just was reading the image that they had posted.

I'll have a look at the download.

John L>
IA|AI

HologenicMan
John A. Latimer
http://www.UniversalHologenics.com

"If the Human brain were so simple that we could understand it,
we would be so simple that we couldn't..."
-Emerson M Pugh-

Current project:http://www.vrconsulting.it/vhf/topic.asp?TOPIC_ID=816&whichpage=1

DISCOVERY: The more I learn, the more I learn how little I know.
GOAL: There's strength in simplicity.
NOTE: Goal not always achieved.
Go to Top of Page

laackejim
Committed Member



USA
3274 Posts

Posted - Dec 10 2007 :  09:17:25  Show Profile  Reply with Quote
Thanks Tobor. I have downloaded and will run on PC tomorrow morning. I cannot get more than the diagram at an unreadable scale on the MAC. BY the way, what version of RealBasic did you use for the XML file? Maybe the suffix was sufficient for my machine to put the RealSoftware logo on the file.

Uncle Jim (e=mc2)
Go to Top of Page

vrossi
Forum Admin



Italy
1455 Posts

Posted - Dec 10 2007 :  10:41:48  Show Profile  Visit vrossi's Homepage  Reply with Quote
I add a direct link to the image here, to be sure that everybody can see it.

It's a great work, even if I had not yet found the time to analyze it in details.

Thank you, Tom, for sharing your work and for adding on your site the links to our Forum and to the RobotInfo site.


Vittorio
virtualhumansforum.com
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 10 2007 :  16:52:36  Show Profile  Visit toborman's Homepage  Reply with Quote
quote:
Mikmoth said

That is way neat... I like how one of the boxes says "Problem Solving"...


Your work on JEM was the inspiration for me to create the diagram. Thanks.


quote:
Grant said

I had to grab a dictionary to understand the comments for "Refer"

It's a good map. A slightly depressing aspect is that any good AI should include routines (or capacity) for almost all those little boxes

This kind of diagram is a great organisational tool if you're coding an AI, kind of like a giant to-do list that also shows planned connections between areas of code. There would need to be more connections between some of the lower boxes, where methods and/or behaviours need more integration together. There would also need to be a great flexibility for change - projects like pioneering AI are very difficult to pre-plan with absolute accuracy!


Yes, I expect many changes. I have coded and implemented most of these functions as indicated on the map, but Iím still testing and refining them. Right now, the integration takes place in the conversationalist behavior. Iím sure I have missed some functions.

quote:
John said

Very nice layout for developing/testing an emerging AI.

I had trouble reading the print on my monitor for some reason which became frustrating, but from what I can read it is well thought out.


Sorry for the small diagram on the web page. I provided the download because I couldnít get the javascript working on the hosting site.

quote:
Jim said

Thanks Tobor. I have downloaded and will run on PC tomorrow morning. I cannot get more than the diagram at an unreadable scale on the MAC. BY the way, what version of RealBasic did you use for the XML file? Maybe the suffix was sufficient for my machine to put the RealSoftware logo on the file.


The web site code was auto generated using a site builder. The download files were auto generated from MS Visio.

quote:
Vittorio said

Thank you, Tom, for sharing your work and for adding on your site the links to our Forum and to the RobotInfo site.


I have learned much from the conversations on the forums. Thank you for making them available.

http://mindmap.iwarp.com
Go to Top of Page

GrantNZ
Dedicated Member



New Zealand
2677 Posts

Posted - Dec 11 2007 :  05:48:48  Show Profile  Reply with Quote
quote:
I have coded and implemented most of these functions as indicated on the map, but Iím still testing and refining them.

Intriguing Are you planning to publicise the results here?
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 11 2007 :  07:23:31  Show Profile  Visit toborman's Homepage  Reply with Quote
I would be happy to share the results of tests, grant. I'll be running some tests tomorrow.

http://mindmap.iwarp.com
Go to Top of Page

mikmoth
Moderator



USA
2082 Posts

Posted - Dec 11 2007 :  08:55:31  Show Profile  Visit mikmoth's Homepage  Reply with Quote
Hey Taborman,

Around here we're used to talking about our projects for months on end and then maybe... maybe... we'll see a result! Are you telling us you've been secretly building this atomic AI behind our backs? This is like going to the movies and findind out there's a new Indiana Jones playing!

Looking forward to seeing what ya got!

http://lhandslide.com

Edited by - mikmoth on Dec 11 2007 08:57:38
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 11 2007 :  16:01:23  Show Profile  Visit toborman's Homepage  Reply with Quote
Nothing atomic. More like Indiana Jones playing with firecrackers. But, it has been in the works for a while.

http://mindmap.iwarp.com
Go to Top of Page

laackejim
Committed Member



USA
3274 Posts

Posted - Dec 11 2007 :  22:51:21  Show Profile  Reply with Quote
quote:
Originally posted by toborman

I would be happy to share the results of tests, grant. I'll be running some tests tomorrow.


That diagram is quite complete, I am tempted to say amazing. So far there is only one place I have a question.

For all but one of the groups I can conceive of a way to make it work. One group seems to me to be unreachable. It is the same group that I have expressed doubts about at other times to other people. My doubts do not mean I think it is impossible, just that I have no idea how it can be accomplished.

That is the group having to do with physical things (gustatory, tactile, etc.). The processing system for those internally mediated sensory inputs and their associated meaning in animals (us included) came about as a part of the evolution of the organism. In a digital, or analog, electronic system I just don't know how those are going to be accommodated. Unless they are redefined in terms relevant to the digital existence. And then, if they are, do they really have the cognitive meaning that led to their placement in the process in the first place?

Please understand that I am not naysaying, or throwing a monkey wrench (boy that dates me) But I am keenly interested.

If at some time you choose to explain how you do it, I would be excited to hear because it is a critical piece and the only one I have not been able to conceive a path to. And No, I have not created anything useful and it is more than just possible that I couldn't, even if I tried really hard. Keep working Tom, I am impressed and pleased that you are moving on it.

With people like you and John out there, this is going to happen.

Uncle Jim (e=mc2)

Edited by - laackejim on Dec 11 2007 22:58:11
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 12 2007 :  02:13:45  Show Profile  Visit toborman's Homepage  Reply with Quote
I have not developed that area yet, and I may run into the problems you suggest. I believe that a suitable representation can be found. I feel that way because I was able to use some visual representations for object recognition on one of my robotics projects for manufacturing. The representations were not neural network based, as one might expect. I think similar data can be devised for the other senses. Thanks for the interest, over time you and I may come up with a solution.

http://mindmap.iwarp.com
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 12 2007 :  03:06:55  Show Profile  Visit toborman's Homepage
grant

here is the conversation log from today's test.

tom made statement hello. what time is it?
Harry made statement how are you.
Harry made statement it is 05:53 PM, Tuesday, December 11, 2007.
tom made statement describe humans.
Harry made statement mammals are humans.
Harry made statement jerks are humans.
Harry made statement james_+george are humans.
tom made statement grant is a human.
Harry made statement I don't know if the statement is true.
Harry made statement I will remember.
Harry made statement grant is a human.
tom made statement grant is smart.
Harry made statement I don't know if the statement is true.
Harry made statement I will remember.
Harry made statement grant is smart.
tom made statement describe grant.
Harry made statement grant is a smart_ human.
tom made statement is grant an animal?
Harry made statement Yes, grant is an animal.
tom made statement prove grant is an animal.
Harry made statement since humans are animals and grant is a human, it follows that grant is an animal.
tom made statement (OK)
Harry made statement Thank you.

http://mindmap.iwarp.com
Go to Top of Page
Page: of 25 Previous Topic Topic   
Next Page
 New Topic  Reply to Topic
 Printer Friendly
Jump To:
Virtual Humans Forum © V.R.Consulting Go To Top Of Page
This page was generated in 0.1 seconds. Snitz Forums 2000