One experiment that I was thinking of trying is to look for a way to interpret the sentences of highly constrained natural language. Much of the problem with interpreting sentences is that it requires a great deal of knowledge in order to guess which of the possible interpretations of the sentences makes the best sense. I might try giving the program a knowledge of many simple stories and of general rules of thumb about the way the constrained ‘world’ works. Then one experiment would be to see if I could write the functions that would allow it to interpret the sentences based on the knowledge about the ‘world’ that it had. I would try to develop some general rules to govern the reading of the stories. For instance various objects of a series of sentences are often linked together by anaphoric-like relations. So I might try some general subprograms to develop possible links from the test stories. Using this system it might be able to relate the possible linkages to the knowledge that it had already acquired. I don’t expect it to work perfectly but I am only looking for some footholds to get to the next level. If I find something that often works then I could simulate combinatorially expensive situations. Because I having some idea about how the different possibilities could make the analysis combinatorially expensive when there is a large database of knowledge that could be related to the possible interpretations, I would be able to simulate this while working with a partially simulated method.I may never actually try this series of experiments; this is just one possible scenario that I made up to try to give you some kind of reply.As far as the implementation of my ideas in relation to the problems of complexity and conceptual relativism my program would start somewhere; I am not saying that there is some fantasy to completely overcoming the problem. But I would want my program to be able to redefine concepts or to create derived concepts and relations in order to handle the relativistic problems that I mentioned. In other words, I consider conceptual relativism to be the situation that has to be dealt with in some way. I intend to work a little on more on my summary and I may try to add some ideas that to get around the problems that complexity and conceptual relativism create.Jim Bromer From: [email protected] Date: Tue, 23 Apr 2013 17:49:29 +0200 Subject: Re: [agi] Summary of My Current Theory For an AGI Program. To: [email protected] Like most here I am mostly perplexed by this manifesto. I could agree with Babiano that the choice of words here and there makes it sound more pseudoscientific than scientific, but as a "practitioner" I am mostly concerned with the missing implementation details. The manifesto started with the idea that complexity shall be defeated, but I don't see how or where, what I do see is that everything will be just too bloody fluid and based on unknown (infinite?) numbers of experiments that sound complex enough. I think in part 6 we see how not relying on embodiment may come back and bite you. You may know the joke about the hungry slave who goes to his cruel master requesting food, and all he gets is glass of water after glass of water, and the question "are you ready to eat something". When the slave after x glasses of water answers "No" the master quips "You see, you were not hungry, you were thirsty all along". For any embodied entity food has to mean food and sex has to mean sex (plugging in the wall socket etc), or it will be the very end of the entity, so I would not welcome any shifts to a range of concepts. If such a set of independent, "grounded" concepts is fixed then we probably enter a Hutterian universe where agents try to maximize their grounded and fixed utility functions with evangelical zeal. However we can still guarantee "individuality" emerging from this simultaneous pursuit of many objectives, as it is a kind of "many-body problem" with extreme sensitivity to initial conditions and therefore chaotic behavior, so even if we think alike I may end up collecting water while you end up collecting food. The elephant in the room is anyway how you are going to implement concepts, you mention something about data structures you have in mind, but in my mind they should be the first to get out of your mind, if you are not out of your mind :) . In particular, if you reject the above proposed "basic insticts" how are you going to bootstrap they concept graph? Which will be the first concept? As has been suggested a lot in the last 60 years, a concept could easily be a program, but then it may not so easily receive those influences you want to see happening. For a tremendous amount of real world data an object hierarchy or ontology is a great concept implementation, you may know that men and women exist, but not about the emo tribe and the Nanguza tribe, then you can assume things about the Nanguza women but perhaps not for the Nanguza rabbit whisperer. Instead, would you prefer shifting the "human" concept left and right to accomodate emo girls and Nanguza rabbit whisperers? I wouldn't. Please try to keep the manifesto tighter (it includes some speculative fluff here and there) and branch out into implementation ASAP AT
------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
