Thursday, November 27, 2003

How to merge Short Memory and Main Memory?

1) What to merge:
- Neuron;
- Reason-Consequence axon.
- Parent-Child axon.
2) Let's consider how to merge on example of Neuron.
3) Neuron has:
- Desirability attribute.
- Strenght attribute.
4) Let's make simplification and assume that we merge Desirability attribute without taking into account Strenght attribute.
5) Legend:
- "sm": short memory.
- "mm": main memory (long-term memory).
- "Desirability_sm": value of Desirability attribute of short memory neuron.
- "Desirability_mm": value of Desirability attribute of main memory neuron.
- "Desirability_mm_afterMerge": Value of the main memory Desirability attribute after merge with "Desirability_sm".
6) Simple solution:
Desirability_mm_afterMerge = (10 * Desirability_mm_beforeMerge + 1 * Desirability_sm_beforeMerge)/ (10+1).
That means that Desirability_mm has 10 time heavier weight than Desirability_sm.
7) More complex solution (takes into account Strength attribute).
Desirability_mm_afterMerge = (Strength_mm_beforeMerge * Desirability_mm_beforeMerge + Strength_sm_before_Merge * Desirability_sm_beforeMerge) / (Strength_mm_beforeMerge + Strength_sm_beforeMerge)
Strength_mm_afterMerge = Strength_mm_beforeMerge + Strength_sm_Delta
Strength_sm_Delta = Strength_sm_beforeMerge - Strength_sm_sinceLastMerge
"Strength_sm_sinceLastMerge" is either Strength_sm which was set at last merge or Strength_sm which was set during creation of sm neuron in active memory.
8) Actually more complex solution should take into account possibility of multiple merge of mm and sm.
In this case we should not update mm by changes in sm which were merged already.
That is:
Desirability_mm_afterMerge = (Strength_mm_beforeMerge * Desirability_mm_beforeMerge + Strength_sm_before_Merge * Desirability_sm_Delta) / (Strength_mm_beforeMerge + Strength_sm_beforeMerge)

Desirability_sm_Delta = Desirability_sm_beforeMerge - Desirability_sm_sinceLastMerge

Strenght will be calculated the same way:
Strength_mm_afterMerge = Strength_mm_beforeMerge + Strength_sm_Delta

9) If we allow multiple merge, then we should know sm_afterMerge value:

Desirability_sm_afterMerge = Desirability_sm_beforeMerge

Desirability_sm_sinceLastMerge(afterMerge) = Desirability_sm_afterMerge (that is we preserve this Desirability value for future calculations of Desirability_sm_Delta)

Strength_sm_afterMerge = Strength_sm_beforeMerge

Strength_sm_sinceLastMerge(afterMerge) = Strength_sm_afterMerge (for the sake of future Strength_sm_Delta calculation)

Tuesday, November 18, 2003

Yahoo! Maps

Grand Opening Celebration

Map: intersection of Patterson, Norriswood and Deloach streets

Wednesday, November 19, 2003
11 AM Ribbon Cutting and Dedication
12 PM - 3 PM: Facility tour, speaker presentations, and technology demonstrations

Friday, November 07, 2003

I'm looking for a Research Partner in True AIS Development

I’m looking for a partner in True Artificial Intelligence System Development research

I. About me:

1. I'm very interesting in research in True Artificial Intelligence field.

2. I'd like to build artificial mind, which will have comparable abilities with humans. That means that this mind will be able to work as office clerk, customer support representative, lawyer, computer programmer, manager, politic, and so on.

3. I have a lot of ideas about how to implement True Artificial intelligence system.
I explained those ideas on my web-site:

4. Currently AI is a hobby to me. But who knows what will happen in future.

II. What kind of help I need:

1. I need someone who will help me to think: two researchers' minds together work much better than separately.
For instance, one person can concentrate on asking questions - another person on giving answers. Also research pair (or group) filter out wrong ideas much quicker, than one researcher alone.
So I need someone to discuss AI development issues.
2. Prototype development.
I think it's time to check my ideas in real prototype.
- Prototype should be carefully selected (not every prototype is a good way to the True Artificial Intelligence System).
- Prototype should be designed.
- Prototype should be implemented/coded/programmed.
I need your help on every stage.

3. I need someone who will help me to improve readability of my site.
If you just read an article(s) from my site and then ask about everything that is unclear to you (or hard to understand) - it would be strong help to me.
You could also correct/rewrite articles to make them readable.

4. I need help in father development of my site.
Your questions and my answers about AI could be good source for new articles on the site.
If you write your articles about AI - it might be also good.

5. I appreciate any new ideas.

III. I'm looking for you if:

1. You have passion about Artificial Intelligence development, if you want to take part in discussion, designing, and development of True Intelligent System.
2. You are ready to spend ~5...20 hours each week for AI research (discussions, design, some coding/programming).
3. You have strong abstract thinking ability.
4. You have strong abstract conversation ability: strong ability to explain your thoughts and strong ability to understand my thoughts.
5. You have strong feeling of understanding: if you see lack of understanding during our conversation, you immediately indicate it.
You are not afraid to ask questions.
6. You are able and like to ask questions.
7. You are able and like to answer questions.
8. You are interested in how things work. You are interested how your mind works.

IV. Desirable (but not necessary) skills and knowledge:

1. Software development. It might be great if you successfully accomplished at least one software project.
It would be even better if you have experience with database management systems, like MS SQL Server or Oracle.
2. Knowledge about how brain/mind works.
3. Knowledge about how conditioned reflex is developed.
4. It is good if you already know why and what for do humans live.
What does define purpose of life?
5. It is good if you able to think about yourself as about machine, which consist of components. It's good if you understand how these components influence each other.

Tutoring Research Group Contact List

Tutoring Research Group Contact List

Max Louwerse Computational Linguist.

Thursday, November 06, 2003

AIS prototype: "Dictionary"

"Dictionary" is a good idea for AIS prototype.
First version of Dictionary can be implemented just by AIS reader implementation. Reader will know what are typical words, phrases, in which context are they used, list of synonims.

Additional features can be added to the Dictionary prototype:
- Google search and update of Dictionary database if user wants to get more detailed explanation of the word.

Energy Limits to the Computational Power of the Human Brain

Energy Limits to the Computational Power of the Human Brain

John Harris (Stan Franklin's team)

9. John Harris, Hypertext as a learning tool, University of Memphis August 1990. Dr. Harris has been awarded several postdoctoral fellowships, and is currently at Lemoyne-Owen College.

LeMoyne-Owen College
807 Walker Avenue
Memphis, TN 38126
Division of Natural Science, Mathematics and Computer Science (901) 942-7333

Map to LeMoyne-Owen College

Uma Ramamurthy (Stan Franklin's team)

Uma Ramamurthy
student of Stan Franklin.
18. Uma Ramamurthy, also ABD began dissertation work concerning an artificial life agent controled by a Copy-cat-like architecture. She's since moved on to issues of memory, learning and self-preservation in autonomous agents, particularly the IDA project.

Project Leader - Information Technology,
Department of Biostatistics,
St. Jude Children's Research Hospital,
332 North Lauderdale,
Memphis, TN 38105-2794
Tel: (901)-495-2100

Map to Uma Ramamurthy

My believes about AIS development: Read words, not characters.

When AIS reads the text it shouldn't bother about meaningfullness of charachters inside a word. Instead AIS should recognize word as a whole. That means that "time" and "timely" are completely different words (because of different spelling). At the same time, AIS can consider "time" and "timely" words as similar/related words, just because they appear in a very similar context.
From AIS point of view words: "mother" and "dad" are much closer to each other than "time" and "tame". In spite of similarity of spelling in "time"/"tame" pair and absolute different spelling in "mother"/"dad" pair. It happens just because "mother" and "dad" words appears in similar context, but "time" and "tame" - don't.

Wednesday, November 05, 2003

Copycat-like architecture overview

Copycat-like architecture overview

Copycat-like architecture overview in text format

My believes about AIS development: "Random" is bad.

"Random" word is bad word in mind of AIS developer. Intelligent System (IS) could be unpredictable, but the more Intelligent System is random the less it is intelligent.

That means that random choice (action selection) is a bad idea.

My believe about AIS development: "How to copy human's mind"

When AIS developer copies human's mind he shouldn't copy absolutely everything.
Some things should be copied, other - shouldn't.

For instance, human brain has several parts: vision, hearing, speech, prononciation, body control. Not all of them should be copied. For instance, vision and hearing are hard to implement. But they could be easily replaced by text parser and Internet browser.

Body control module (blood pressure, temperature, muscles control, ...) is not necessary for AIS, because AIS is not supposed to live in cave/forest or care about food.

Another example: in human brain some neurons are located close to each other, some - far from each other. As a result some neurons are strongly connected by axons, other - weakly connected (or not connected at all).
The reason of that is physical limitation of brain. Such limitation shouldn't be implemented in artificial mind.
Home page of Stan Franklin


Stan Franklin's book: "Artificial Minds"

Stan's map

Stan Franklin Dunavant University Professor
Computer Science Phone: (901) 678-3142
Univ of Memphis Fax: (901) 678-2480
Memphis, TN 38152
Concise definition is not the best way to define a concept. The best definition easily creates clear thought about the concept in the reader's mind.

Unfortunately concise definition requires that reader reads this definition several times, plays with this definition, and only then reader will understand what does author mean.

So, in spite that good definition is longer than concise definition, reader understands good definition faster and better than precise definition.

So, what is the good definition: it's list of other concepts, words and phrases, synonims, and examples.
Conscious and selfconscious:
Conscience is abstract thinking. Mind is conscious if it manipulates abstract concepts (which are not directly related with outer world).
Self-consciense appears when mind starts thinking about itself.
Because "myself" is relatively complex concept, selfconsciousness should be considered as higher level of consciousness (in comparison with consciousness without thinking).
Dr Arthur Graesser

Research Interests

General areas of cognitive science, discourse processing, artificial intelligence, and information processing. More specific interests include knowledge representation and organization, computational procedures, text comprehension, reading, question asking and answering, tutoring, inference generation, conversation, memory, learning, problem solving, human and computer tutoring, writing, expert systems, design of educational software, and human-computer interaction.

Questions to Stan Franklin:
1) What is a "Conscience"?
2) What are relations and hierarchy of "reflexes", "emotions", and "thoughts"?
3) How to improve readability of my site?
4) What are the main steps in Artificial Mind development?
5) Am I correct about selecting the prototype (Reader -> Writer -> Chatter)?
6) What is "the grand opening on November 19th"?
What's wrong with my current AIS development process:
1) I need someone who will check my thoughts on daily basis.
2) I need someone, who will concentrate on questions, when I'll concentrate on answers.
3) I need someone, who will concentrate on answers, when I'll concentrate on questions.
4) I need someone who will do part of the work.
5) I need someone who will define goals in development. I can define goals by myself, but in this case it would be better if someone else implement these goals.
6) I need a source of enthusiasm in the development.
Discussion about the development is good source of such enthusiasm.