Mike, > >Six 2003 >Seven 1996 >Eight 2001 >Eight and a half Good point with the movies, only a hardcore movie fan would make that association early in his trials to figure out the pattern as movie dates. In this case you gave a hint, such a hint would tell the system to widen its attention spotlight to inlude "movies", so entertainment, events, celebration, etc would come under attention based on what structure the movie concept's parent has in its domain content. Thinking imaginatively to find hard solutions as you say, is possible with this system, by telling it to "think outside the box" to other domains and it can learn this pattern of domain- hopping based on the reward of a success or being authorized to value cross-domain attention search. Thinking for the system is: shifting its attention to different regions (with the 4 domains), sizing and orienting the attention scale, and setting the focus depth (of details); it can then read the contents of what comes up from that region and Compare, Contrast, Combine it to anyalyze or synthesize it. Thinking bigger or narrower is almost literal. Like humans, this system stops a behavior (e.g, stops searching) because it runs out of motivation value, not ideas to search. Many systems known or described can lend themself to brute force thinking unsure of a solution, this structure allows it to do it elegantly using human-centric concept domains "first" (easier for us to communicate to it this way by saying "build a damn good engine" as human do vs 0010101101 or any other non-human language). It can and does re-write the concepts and content in its domain as it learns, but it started with the domains humans give it, e.g., I knew what movies were by having live in a number of situations where this concept was built up, so that later, I can learn about independent films and live performances or new types of entertainment thta gives similar or unfamiliar emotions. Further rational 1) What humans do: have a biased (value system) that makes sense relative to our biological architecture; Generate all human knowledge in this representation structure (natural language, ambiguous, low logic language). 2) What an early AGI can do: learn the human-bias by having a similar architecture which includes the value bias for pattern humans seek. Obtain as much of the recorded knowledge in the world from humans. Generate more, faster, new and better knowlege. "Better" is because it knows our value system and as well knows humans enough to convince them in a diccussion unlike most of us, that better is what it wants us to do(very bad!). For natural language processing, humans readily communicate in song and poems, and understand them. Many songs and poems do not make any logical sense, and few songs have wording order and story elements that are reasonable. The model makes sense by looking for patterns where humans do, in the beats (situational border that structure all input) and the value (emotional meaning) of the song/poems content. Hope some of this helps Robert
--- On Sun, 12/28/08, Mike Tintner <[email protected]> wrote: From: Mike Tintner <[email protected]> Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: [email protected] Date: Sunday, December 28, 2008, 11:38 PM Robert, Thanks for your detailed, helpful replies. I like your approach of operating in multiple domains for problemsolving. But if the domains are known beforehand, then it's not truly creative problemsolving - where you do have to be prepared to go in search of the appropriate domains - and thus truly cross domains rather than simply combining preselected ones. I gave you a perhaps exaggerated example just to make the point. You had to realise that the correct domain to solve my problem was that of movies - the numbers were the titles of movies and the dates they came out. If you're dealing with real world rather than just artificial creative problems like our two, you may definitely have to make that kind of domain switch - solving any scientific detective problem, say, like that of binding in the brain, may require you to think in a surprising, new domain, for which you will have to search long and hard (and possibly without end). Mike, Very good choice. > But the system always *knows* these domains beforehand - and that it must > consider them in any problem? YES the domains "content structure" is what you mean, are the human-centric ones provided by living a childs life loading the value system with biases such as humans are warm and candy is really sweet. By further being pushed thru western culture grade level curriculum we value the visual features symbols "2003" and "1996" as "numbers", then as "dates". The content models (concept patterns) are build up from any basic feature to form instance from the basic content of the four domain, such as "dates of leap years", "century marks", "millenium" or "anniversary". problems more like: -- "ice cream favorite red happee" -- What this group of words means has everything to do with what the reader knows and values beforehands. And what he values will determine what his attention is on, the food, the emotions, the color, the positions; or how deep the focus is: on the entire situation (sentence), a group of them, a single word or a letter. Humans value from the top so we'll likely think of cherry ice cream before we see: the occurance pattern of letter "e" in every word in that 'sentence' above. Good choice for your problem: Six 2003 Seven 1996 Eight 2001 Eight and a half ---- ? (i see a number of patterns, such as "00" "99", multiply, add word to end - but haven't gotten the complete formula) For the system, it is biased; it make sense for itself, it's internal value. The answer the system chooses is the one that makes sense to what it knows and values. Sure, it can and will be used as a general pattern mining by comparing and contrasting within lines, line-to-line, number-to-text, text-to-number, date-to-word, month-to-number, middle-part to end, end-to-end, etc, until a resulting comparison yeilds a pattern that it values (from experience or being "told"). However, the value system controlling attention prevents any combinatorial explosion - animals only search through the models that have value (indirectly or directly) to the problem situation, thus limiting the total gueses we could even make (it looks for patterns it already knows). To solve problems it has not been taught or can't see a pattern for: 1) If self-motivated because a reward/avoidance is strong: Keeps looking for patterns 3-C by persiting in its behavior (doing the same ol thing) and fail. If a value happens to occur in one of the result when it kept going, it will see that something was different. It has acces to its own actions (role and relation domain) and this different action stands out (auto-contrast) and become of greater value due to the associated difference (non-failure). It keeps trying until the motivation runs out (energy level decays) or other value or past experiences exceeds its model of how long it should take.. 2) Instructed how to solve it by trying x, y or x. "Wden your attention", "expand your focus" - then it has a larger set of regions to try and find a pattern it values. If set, it can examine regions of the instruction (x, y , and z) and see what was different from what it was trying (if the comparision yeilds a high enough value, it will try those as well). "Try going left and up" O.K. auto-contrast "I was trying only up: the difference is to add one more direction; I can try left and up and back" etc.. Creativity and reason come from the 3-C mechanism Creativity in the model is to combine any sets of domain content and give it a respective value from its experience and domain models. Example: Combine the form of a computer mouse, the look of diamonds, the function of a steering wheel, with the feel of leather: what do you get? Focus on each region and combine, then e-valuate (compare it to objects, functions). What's your result? Models in my experience say that it's a luxury-car controller; while you might say it would be something in an art galleryy, etc (art, value without function/role). Anyway, Bens, pre-school for AGI is one of the means to bias such a system with experience and human values; another way is to try to properly represent human experience (static and dynamic) and then essentially implanting memories and "experience" instead of just declarative facts. Robert --- On Sun, 12/28/08, Mike Tintner <[email protected]> wrote: From: Mike Tintner <[email protected]> Subject: Re: Human-centric AGI approach-paper (was Re: Indexing and Re: [agi] AGI Preschool: sketch of an evaluation framework for early stage AGI systems aimed at human-level, roughly humanlike AGI To: [email protected] Date: Sunday, December 28, 2008, 8:38 PM Robert: Example: Here's a pattern example you may not have seen before, but by 3C you discover the pattern and how to make an example: As spoken aloud: five and nine [is] fine two and six [is] twix five and seven [is] fiven Robert, So, if I understand, you're designing a system to deal with problems concerning objects, which have multiple domain associations. For example, words as above are associated with their sounds, letter patterns, and perhaps meanings. But the system always *knows* these domains beforehand - and that it must consider them in any problem? It couldn't say find the pattern to a problem like: Six 2003 Seven 1996 Eight 2001 Eight and a half ---- ? where it wouldn't know any domain relevant to solving the problem, and would first have to *find* the appropriate domain?. (In creative, human-level intelligence problems you often have to do this). agi | Archives | Modify Your Subscription agi | Archives | Modify Your Subscription agi | Archives | Modify Your Subscription ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
