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
Previous Page | Next Page
Author Previous Topic Topic 
Page: of 25

laackejim
Committed Member



USA
3274 Posts

Posted - Dec 23 2007 :  23:02:33  Show Profile  Reply with Quote
quote:
Originally posted by toborman

Now we need to teach Harry to find a previous statement to answer the question “why”.

tom : hello. what time is it?
Harry : how are you.
Harry : it is 09:30 AM, Sunday, December 23, 2007.
tom : is jim an animal?
Harry : Yes, jim is an animal.
tom : why?
Harry : since humans are animals and jim is a human, it follows that jim is an animal.
tom : (OK)
Harry : it's been a pleasure.



Hot Diggety Dog, Thanks Harry, my optimism is growing large again.

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

toborman
Hooked Member



USA
289 Posts

Posted - Dec 23 2007 :  23:12:19  Show Profile  Visit toborman's Homepage  Reply with Quote
quote:
by ken

Does Harry handle "prove" differently than "why"?


“Why” is interpreted as “prove” last statement.

quote:
by ken

When Harry is asked "is jim an animal?", is Harry remembering his prior answer or is he rethinking the answer?


He is rethinking the answer.

Btw, I got your e-mail. I don’t need another VB right now, thanks.

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

toborman
Hooked Member



USA
289 Posts

Posted - Dec 28 2007 :  18:09:35  Show Profile  Visit toborman's Homepage  Reply with Quote
What roles would you find most beneficial in an AI agent? Choose from the list, or suggest your own. Maybe the top three choices will tell us what is important to you.

Advisor
Assistant
Conversationalist
Customer service representative
Companion
Director
Diagnostician
Interviewer
Investigator
Learner
Logician
Mathematician
Orator
Predictor
Puzzler
Reader
Salesperson
Stock analyst
Storyteller
Teacher
Thinker
Writer

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

laackejim
Committed Member



USA
3274 Posts

Posted - Dec 28 2007 :  21:30:51  Show Profile  Reply with Quote
quote:
Originally posted by toborman

What roles would you find most beneficial in an AI agent? Choose from the list, or suggest your own. Maybe the top three choices will tell us what is important to you.



I have stuck together the activities that seem to flow together with the primary function first and flowing down in priority. My interests are more in a personal interface than in a sales/service interface. I think that the former is where the difficult/delicate/critical path lies, the latter is already a growing capability.

AdvisorAssistant (Predictor??)

CompanionConversationalistPuzzlerLogician


Mathematician (Probably only to access some of the elegant visual math display programs)


ReaderLearnerThinkerTeacher



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

toborman
Hooked Member



USA
289 Posts

Posted - Dec 29 2007 :  01:04:52  Show Profile  Visit toborman's Homepage  Reply with Quote
How to determine the soundness of an argument (i.e., syllogism):

Form 1: [Since | because | for | given that | due to | insofar as | inasmuch as | in view of | as shown by | can be inferred from | on the ground that | blank] [all] Xs are Ys and A is an X, [thus | therefore | accordingly | it follows that | implies that | hence | consequently | so | we may infer that | we may conclude that | in conclusion] A is a Y.

Form 2: [we may infer that | we may conclude that | blank ] A is a Y, [Since | because | given that | due to | in view of | as shown by | can be inferred from | on the ground that ] [all] Xs are Ys and A is an X.

If form is correct and A = A, X = X, Y = Y, then the argument is “valid” otherwise the argument is “invalid”.

If the argument is “valid” and the premises are true, then the argument is “sound” otherwise the argument is “unsound”.

Non-standard forms should be converted to standard forms before evaluation.

If the terms are not equal, they may be resolved with synonyms.

If the truth of any premise is unknown, it may be resolved with multi-level deduction.

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

bodylanguage
Curious Member



15 Posts

Posted - Dec 29 2007 :  01:24:02  Show Profile  Reply with Quote
so if i learn to understand this schematik i can own all the virtual human,., man i wnat to make a real life scarey movie thank,.
Go to Top of Page

laackejim
Committed Member



USA
3274 Posts

Posted - Dec 30 2007 :  05:48:51  Show Profile  Reply with Quote
quote:
Originally posted by toborman

How to determine the soundness of an argument (i.e., syllogism):

Form 1: [Since | because | for | given that | due to | insofar as | inasmuch as | in view of | as shown by | can be inferred from | on the ground that | blank] [all] Xs are Ys and A is an X, [thus | therefore | accordingly | it follows that | implies that | hence | consequently | so | we may infer that | we may conclude that | in conclusion] A is a Y.

Form 2: [we may infer that | we may conclude that | blank ] A is a Y, [Since | because | given that | due to | in view of | as shown by | can be inferred from | on the ground that ] [all] Xs are Ys and A is an X.

If form is correct and A = A, X = X, Y = Y, then the argument is “valid” otherwise the argument is “invalid”.

If the argument is “valid” and the premises are true, then the argument is “sound” otherwise the argument is “unsound”.

Non-standard forms should be converted to standard forms before evaluation.

If the terms are not equal, they may be resolved with synonyms.

If the truth of any premise is unknown, it may be resolved with multi-level deduction.



I think I follow it okay. The weak spots would appear to be the last resorts, synonyms and multi-level deduction. The more you know about the person interacting (as far as how he uses language and what, in his mind are synonyms the better you get.

All in all it looks like it flows. This chain is the first place where fuzzy logic MAY contribute. One place is in shading synonyms and assisting in balancing the "=" requirement with a degree of reality (there are very very few yes/no meanings in language)

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

toborman
Hooked Member



USA
289 Posts

Posted - Dec 30 2007 :  07:58:18  Show Profile  Visit toborman's Homepage  Reply with Quote
quote:
Originally posted by laackejim

quote:
Originally posted by toborman

How to determine the soundness of an argument (i.e., syllogism):

Form 1: [Since | because | for | given that | due to | insofar as | inasmuch as | in view of | as shown by | can be inferred from | on the ground that | blank] [all] Xs are Ys and A is an X, [thus | therefore | accordingly | it follows that | implies that | hence | consequently | so | we may infer that | we may conclude that | in conclusion] A is a Y.

Form 2: [we may infer that | we may conclude that | blank ] A is a Y, [Since | because | given that | due to | in view of | as shown by | can be inferred from | on the ground that ] [all] Xs are Ys and A is an X.

If form is correct and A = A, X = X, Y = Y, then the argument is “valid” otherwise the argument is “invalid”.

If the argument is “valid” and the premises are true, then the argument is “sound” otherwise the argument is “unsound”.

Non-standard forms should be converted to standard forms before evaluation.

If the terms are not equal, they may be resolved with synonyms.

If the truth of any premise is unknown, it may be resolved with multi-level deduction.



I think I follow it okay. The weak spots would appear to be the last resorts, synonyms and multi-level deduction. The more you know about the person interacting (as far as how he uses language and what, in his mind are synonyms the better you get.

All in all it looks like it flows. This chain is the first place where fuzzy logic MAY contribute. One place is in shading synonyms and assisting in balancing the "=" requirement with a degree of reality (there are very very few yes/no meanings in language)



Converting from non standard forms to standard forms is also a non trivial task.

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

GrantNZ
Dedicated Member



New Zealand
2677 Posts

Posted - Dec 30 2007 :  08:15:31  Show Profile  Reply with Quote
And back again, if you want to sound colloquial and natural
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 31 2007 :  01:05:05  Show Profile  Visit toborman's Homepage  Reply with Quote
mind map site has been updated with models, motivation, and an interviewer role.

http://mindmap.iwarp.com

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

laackejim
Committed Member



USA
3274 Posts

Posted - Dec 31 2007 :  18:12:25  Show Profile  Reply with Quote
quote:
Originally posted by toborman


Converting from non standard forms to standard forms is also a non trivial task.



I may have missed something but for me the conversion from non-standard to standard was straight forward. However, I saw and ran into 2 Big problems (for me at least)
1. Keeping track of the non-standard forms and what they mean. For contemporary slang this is an ongoing, constantly changing world, and unless you have an army of cooperating teenagers to help you keep up you will never make it.
2. Conversion from non-standard to standard to non-standard has the same peculiar problems that the XYZ axis system in 3D graphics has. The XYZ axis system is straight forward and intuitive, move, turn, roll, all easy. However, if the same thing is animated iin a different order, or the actions are taken from a different starting point, and you don't end up where you want. The HPB system (Euler math?) was created to solve that problem. The animations work fine but setting them up is a mind bender.

Going back to non-standard form idiom has to carry with it all the accumulated meanings in the words and alter them slightly so they fit the starting point and the meaning of the conversation. Easy if you are a highschool teen but ---

Grant, Perhaps that is why my target AI (does not exist completely) would always speak in standard, educated, forms. It is easier, much easier.


Uncle Jim (e=mc2)

Edited by - laackejim on Dec 31 2007 18:14:00
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - Dec 31 2007 :  20:18:50  Show Profile  Visit toborman's Homepage  Reply with Quote
quote:
Originally posted by laackejim

quote:
Originally posted by toborman


Converting from non standard forms to standard forms is also a non trivial task.



I may have missed something but for me the conversion from non-standard to standard was straight forward. However, I saw and ran into 2 Big problems (for me at least)
1. Keeping track of the non-standard forms and what they mean. For contemporary slang this is an ongoing, constantly changing world, and unless you have an army of cooperating teenagers to help you keep up you will never make it.
2. Conversion from non-standard to standard to non-standard has the same peculiar problems that the XYZ axis system in 3D graphics has. The XYZ axis system is straight forward and intuitive, move, turn, roll, all easy. However, if the same thing is animated iin a different order, or the actions are taken from a different starting point, and you don't end up where you want. The HPB system (Euler math?) was created to solve that problem. The animations work fine but setting them up is a mind bender.

Going back to non-standard form idiom has to carry with it all the accumulated meanings in the words and alter them slightly so they fit the starting point and the meaning of the conversation. Easy if you are a highschool teen but ---

Grant, Perhaps that is why my target AI (does not exist completely) would always speak in standard, educated, forms. It is easier, much easier.





It is easier to speak standard English than interpret it, because we can control our own words and can’t control the words of those who speak to us, therefore, Harry doesn’t try to speak non-standard English, only interpret it. However, even standard English has 512 types of syllogism, 19 of which are valid. These are straightforward to interpret, but the volume makes it non-trivial.

In addition, the use of synonyms complicates the issue, as well as, multi-level deductive methods for determining the truth of the premises.

The acquisition of changing language over time must be addressed through inductive reasoning and agreements between conversing parties, as it is between humans. Harry already has a minimal language learning function.

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

laackejim
Committed Member



USA
3274 Posts

Posted - Jan 01 2008 :  01:26:37  Show Profile  Reply with Quote
quote:
Originally posted by toborman

quote:
Originally posted by laackejim

quote:
Originally posted by toborman


Converting from non standard forms to standard forms is also a non trivial task.



I may have missed something but for me the conversion from non-standard to standard was straight forward. However, I saw and ran into 2 Big problems (for me at least)
1. Keeping track of the non-standard forms and what they mean. For contemporary slang this is an ongoing, constantly changing world, and unless you have an army of cooperating teenagers to help you keep up you will never make it.
2. Conversion from non-standard to standard to non-standard has the same peculiar problems that the XYZ axis system in 3D graphics has. The XYZ axis system is straight forward and intuitive, move, turn, roll, all easy. However, if the same thing is animated iin a different order, or the actions are taken from a different starting point, and you don't end up where you want. The HPB system (Euler math?) was created to solve that problem. The animations work fine but setting them up is a mind bender.

Going back to non-standard form idiom has to carry with it all the accumulated meanings in the words and alter them slightly so they fit the starting point and the meaning of the conversation. Easy if you are a highschool teen but ---

Grant, Perhaps that is why my target AI (does not exist completely) would always speak in standard, educated, forms. It is easier, much easier.





It is easier to speak standard English than interpret it, because we can control our own words and can’t control the words of those who speak to us, therefore, Harry doesn’t try to speak non-standard English, only interpret it. However, even standard English has 512 types of syllogism, 19 of which are valid. These are straightforward to interpret, but the volume makes it non-trivial.

In addition, the use of synonyms complicates the issue, as well as, multi-level deductive methods for determining the truth of the premises.

The acquisition of changing language over time must be addressed through inductive reasoning and agreements between conversing parties, as it is between humans. Harry already has a minimal language learning function.



Very good Tom. Very Good.

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

toborman
Hooked Member



USA
289 Posts

Posted - Jan 07 2008 :  01:55:33  Show Profile  Visit toborman's Homepage  Reply with Quote
mind map site has been updated with new operation function.

http://mindmap.iwarp.com

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

toborman
Hooked Member



USA
289 Posts

Posted - Jan 13 2008 :  23:54:25  Show Profile  Visit toborman's Homepage
New code page added to mind map site provides sample code from the Harry Workman AI project.

http://mindmap.iwarp.com
Go to Top of Page
Page: of 25 Previous Topic Topic   
Previous Page | 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 0.17 seconds. Snitz Forums 2000