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

TheMikh28
Curious Member



USA
39 Posts

Posted - Apr 28 2010 :  22:32:27  Show Profile  Reply with Quote
quote:
I remember your binary approach and weightstack description from the fadela project. Have these approaches been fruitful for your acquisition program?


Though I haven't formally written the code for the language acquisition module at this point, I do have my ideas about how I can algorithmically approach it documented.

The binary approach has indeed proven very fruitful with respect to this though. The weighstack structure is less useful for identifying patterns (and thus acquiring language). However, it is very useful for prioritizing the semi-random selection of articles of information in a given weightstack object on the basis of how frequently the information is used or accessed.

[M*P]

Edited by - TheMikh28 on Apr 28 2010 22:33:35
Go to Top of Page

toborman
Hooked Member



USA
289 Posts

Posted - May 29 2010 :  08:06:39  Show Profile  Visit toborman's Homepage  Reply with Quote
Problem solving dialog using oneof Mill's methods.

Tom: I have a stomachache.
Harry: Who else has a stomachache?
Tom: mom, dad, and sis.
Harry: Did you all eat at the same place recently?
Tom: Yes, we ate a buffet dinner together.
Harry: What did you eat?
Tom: oyster and salad.
Harry: What did mom eat?
Tom: oyster, beef, salad and noodles.
Harry: What did dad eat?
Tom: oyster and noodles.
Harry: What did sis eat?
Tom: oyster and beef.
Harry: since everyone ate oyster, oyster is the probable cause of the stomachache.
Tom: How did you arrive at this answer?
Harry: I used Millís Method of Agreement.
Tom: list the steps you took.
Harry: I collected all the cases with the same effect, compared the effect to the rules to create a list of candidate rules, compared the candidate rules to the situation to find a relevant rule, compared the causal side of the rule to each case to create a list of possible causes and compared the possible causes for each case to find a common cause for all cases.

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

toborman
Hooked Member



USA
289 Posts

Posted - May 30 2010 :  22:42:15  Show Profile  Visit toborman's Homepage  Reply with Quote
Problem solving dialog using Mill's Second method.

Tom: Some of my family has stomachaches.
Harry: Who has a stomachache?
Tom: mom, dad, and sis.
Harry: Do you have a stomachache?
Tom: No.
Harry: Did you all eat at the same place recently?
Tom: Yes, we ate a buffet dinner together.
Harry: What did you eat?
Tom: oyster, beef and noodles.
Harry: What did mom eat?
Tom: oyster, beef, salad and noodles.
Harry: What did dad eat?
Tom: oyster, beef, salad and noodles.
Harry: What did sis eat?
Tom: oyster, beef, salad and noodles.
Harry: since everyone who ate salad has stomachaches and you did not eat salad and you donít have a stomachache, salad is the probable cause of the stomachaches.
Tom: How did you arrive at this answer?
Harry: I used Millís Method of Difference.
Tom: list the steps you took.
Harry: I collected all cases with the same event, compared the effect to rules to create list of candidate rules, compared the candidate rules to the situation to find a relevant rule, compared causal side of rule to recent events to create list of possible causes, compared possible causes for each case. Since all causes are common except one, and all effects are in common except one then the exception is the probable cause

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

toborman
Hooked Member



USA
289 Posts

Posted - May 31 2010 :  04:07:14  Show Profile  Visit toborman's Homepage  Reply with Quote
Problem solving dialog using Mill's Joint Method.

Tom: Some of my family has stomachaches.
Harry: Who has a stomachache?
Tom: mom, dad, and sis.
Harry: Do you have a stomachache?
Tom: No.
Harry: Did you all eat at the same place recently?
Tom: Yes, we ate a buffet dinner together.
Harry: What did you eat?
Tom: oyster and noodles.
Harry: What did mom eat?
Tom: oyster, beef, salad and noodles.
Harry: What did dad eat?
Tom: oyster, beef and noodles.
Harry: What did sis eat?
Tom: oyster, beef and salad.
Harry: since everyone who ate beef has stomachaches and you did not eat beef and you donít have a stomachache, beef is the probable cause of the stomachaches.
Tom: How did you arrive at this answer?
Harry: I used Millís Joint Method.
Tom: list the steps you took.
Harry: I collected all cases with the same event, compared the effect to rules to create list of candidate rules, compared the candidate rules to the situation to find a relevant rule, compared causal side of rule to recent events to create list of possible causes, compared possible causes for each case. Since a common cause matches the common effects and that cause is not in common with the negative effect, then the common cause is the probable cause


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

toborman
Hooked Member



USA
289 Posts

Posted - May 31 2010 :  16:56:09  Show Profile  Visit toborman's Homepage  Reply with Quote
Problem solving dialog using Mill's method of residues.

Tom: I have a stomachache.
Harry: What have you eaten recently?
Tom: oyster, beef, salad and noodles.
Harry: Who did not get a stomachache?
Tom: dad, mom and sis.
Harry: What did dad eat?
Tom: dad ate oyster.
Harry: What did mom eat?
Tom: mom ate beef.
Harry: What did sis eat?
Tom: sis ate salad.
Harry: since you ate oyster, beef, salad and noodles.and you have a stomachache, and others ate oyster, beef, and salad and did not get a stomachache, then the probable cause of your stomachache is noodles.
Tom: How did you arrive at this answer?
Harry: I used Millís Method of Residues.
Tom: list the steps you took.
Harry: I compared the effect to rules to find a relevant rule, compared causal side of rule to this case to create list of possible causes, and collected all cases with counterexamples of each cause. Since the counterexamples eliminated all causes but one, then the remaining cause is the probable cause.

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

toborman
Hooked Member



USA
289 Posts

Posted - May 31 2010 :  21:31:09  Show Profile  Visit toborman's Homepage  Reply with Quote
Problem solving dialog using Mill's method of concommitent variation.

Tom: I have a mild stomachache.
Harry: What have you eaten recently?
Tom: I ate one oyster.
Harry: Who else has a stomachache?
Tom: dad and sis.
Harry: What did dad eat?
Tom: dad ate ten oysters.
Harry: What did sis eat?
Tom: sis ate five oysters.
Harry: How bad is dadís stomachache?
Tom: Severe.
Harry: How bad is sisís stomachache?
Tom: Moderate.
Harry: since everyone ate a different amount of oysters, and each personís stomachache pain varied relative to the amount each ate, then the probable cause of the stomachaches is oysters.
Tom: How did you arrive at this answer?
Harry: I used Millís Method of Concomitant Variation.
Tom: list the steps you took.
Harry: I compared the effect to rules to find a relevant rule, compared causal side of rule to this case to create list of possible causes, collected all cases with the same possible cause, measured the effect for each case, measured the cause for each case, and compared the measurements for each cause and effect. Since the amount of change in the effect is relative to the amount of change in cause for each case, then it is the probable cause.

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

toborman
Hooked Member



USA
289 Posts

Posted - Jun 05 2010 :  04:34:22  Show Profile  Visit toborman's Homepage  Reply with Quote
updated human mind map site with problem solver role, problem solving methods list, case-based reasoning process, diagnosis methods of Mill, and language aquisition process.

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

toborman
Hooked Member



USA
289 Posts

Posted - Jun 10 2010 :  08:15:12  Show Profile  Visit toborman's Homepage  Reply with Quote
updated mind map diagram with sense and motion categories of intelligence. the new diagram is available for download at the mindmap site.

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

toborman
Hooked Member



USA
289 Posts

Posted - Aug 17 2010 :  08:56:47  Show Profile  Visit toborman's Homepage  Reply with Quote
updated the human mind map web site to provide links to the mind map, Harry workman (an intelligent agent), questions for evaluating and certifying intelligent agents, and links to artificial intelligence web sites.

nothing new, just restructuring.

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

toborman
Hooked Member



USA
289 Posts

Posted - Sep 01 2010 :  11:47:09  Show Profile  Visit toborman's Homepage  Reply with Quote
Added links to procedures for the roles Learner and Predictor to the Human Mind Map web site Roles. Added Student to Roles.

Added following procedures:

Learning for prediction
1. observe = collect new data relationships
1.1 for spatial learning = acquire knowledge about size and shape of objects
1.2 for causal learning = acquire knowledge about antecedents, behavior, and consequents of events
2. create model = identify and define related data (hypothesis)
3. design experiment = choose steps to test hypothesis (first time: mimic behavior)
3.1 mimic = attempt recreation of observed behavior to test understanding and repeatability
4. create prototype = choose data to test hypothesis
5. test prototype = try the steps with the data
6. revise = if test fails, try new hypothesis

-

Making predictions

1. Choose a model based on experience.

2. Apply current antecedents to the model.

3. Simulate model behavior.

4. Observe consequents for this model.

5. Make prediction.

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

toborman
Hooked Member



USA
289 Posts

Posted - Jan 23 2011 :  06:29:57  Show Profile  Visit toborman's Homepage  Reply with Quote
I'm looking into a new area and could use some help.
Metacognition variously refers to memory-monitoring and self-regulation, meta-reasoning, consciousness/awareness and auto-consciousness/self-awareness. In practice these capacities are used to regulate one's own cognition, to maximize one's potential to think, learn and to the evaluation of proper ethical/moral rules.
In the domain of experimental psychology, an influential distinction in metacognition is between Monitoringómaking judgments about the strength of one's memoriesóand Controlóusing those judgments to guide behavior.

Where does metacognition fit in the mind map? How does one represent human thoughts? How can metacognition be implemented in an intelligent agent like Harry?

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

mikmoth
Moderator



USA
2082 Posts

Posted - Jan 23 2011 :  06:41:06  Show Profile  Visit mikmoth's Homepage  Reply with Quote
I've gone down this road before... I ended up at a strange place called the "random seed".

Well... in order for you bot to acumulate metacognition he would need real world experiences. Or these could be simulated just by user input. Then you would need an ethic or moral template or a personality template to give him the ability to cross-reference his material with his own view of things.

This is all fine and dandy but how do you produce a personality template or an ethical template in the most natural organic way? You don't... you have to hard-code that in. Or you can use a random seed to simulate the unknown. The unknown that every human has coming into this world? Will he be a good child? A moral child? Will he have obssessive tendencies? Will he be a drug addict? Will he be mentally ill? Does he like to learn? Does he want to become a better person and add substance to the universe? Etc... With a random seed you could at least simulate this unknown.

That's my take...

Great area you're exploring. Hope to hear more.


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

toborman
Hooked Member



USA
289 Posts

Posted - Mar 21 2011 :  08:00:20  Show Profile  Visit toborman's Homepage  Reply with Quote
Added test to certification section in the human mind map.
Test of language acquisition of syntax patterns using inductive reasoning, i.e., learning by example.
Current Inputs are compared to inputs from prior conversations, looking for similar syntax patterns. Any new pattern is remembered.
Test sample:
Given: Verify Tom is Tall.
Given: Verify Jane is cute.
(pattern discovered and remembered.)
Q: Describe Verify syntax.
A: Verify syntax is probably "Verify &variable is &variable."

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

toborman
Hooked Member



USA
289 Posts

Posted - Mar 23 2011 :  05:36:08  Show Profile  Visit toborman's Homepage  Reply with Quote
Added a second test for syntax recognition. The syntax function assigns a category for each variable term in the syntax.

Given: Tom is a human.
Given: Jane is a human.
Given: Tall is an attribute.
Given: Cute is an attribute.
Given: Tom is Tall.
Given: Jane is cute.
Given: Verify Tom is Tall.
Given: Verify Jane is cute.
Q: Describe Verify syntax.
A: Verify syntax is probably "Verify &human is &attribute."

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

toborman
Hooked Member



USA
289 Posts

Posted - Apr 19 2011 :  23:15:30  Show Profile  Visit toborman's Homepage
Added a completely reformatted Human Mind Map to the download page. It also uses a new pan and zoom window that I hope fixes the sizing problem. Let me know what you think.

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 0.16 seconds. Snitz Forums 2000