One method that represents a compressed form of reasoning comes from old AI. If all x has the property 'a', and 'b' is x, then we know by form that 'b' has the property 'a'. This kind of reasoning can be used quite frequently but most of the time we have the situation where we know that although many x have the property of 'a' we cannot definitely conclude that 'b' has the property 'a' just because it is x.
However, with more complicated ideas we can use this kind of expectation to sense when an idea does not make much sense to us. "I had a cupcake but I gave it away. It was delicious." This statement seems to imply that either I had some of the cupcake before I gave it away. But what about this one: "I had a cupcake but I had to give it away before I had any. It was delicious." That statement would seem a little curious to someone who thought about it a bit. It really requires some additional explanation. But we often just go over statements like that without thinking about them very deeply because they don't seem that important to us. How about this one: "I was going to deposit the check you gave me to your bank account as you asked me to but then I thought that wasn't such a great idea. It's in the bank." Do you think that statement would catch your attention if you had asked someone to deposit a check into your bank account? Once you begin analyzing a statement that is important to you the discontinuities of the implied expectations can really jump out. That is an example of logic but it is not an example of Boolean Logic but of applied logic, the application of logic to a situation in which the possibilities belong to categories that can stand out in stark relief. Even if the possibilities (of the expectations) are not logically rigid, logical systems can still be formed to explore the possibilities. Jim Bromer On Wed, Dec 2, 2015 at 2:05 PM, Jim Bromer <[email protected]> wrote: > One other thing that I started thinking of earlier. Suppose you have a > Bayesian method that finds the most likely responses to a multiple > choice event. If the likelihood of the range of responses (or > event-actions) were constantly changing, the pure Bayesian method > could not reliably predict the more likely responses. Interestingly, > it could not predict it even if the likelihood was changing in a > periodic manner. (It would require an additional abstraction of > analysis.) If the number of possible event-actions were great enough > the possible orderings could quickly go out of range. So the > complexity argument is definitely relative to Bayesian methods as > well. (That is not what I was thinking about before, I lost the > previous thought as I thought about that. But it was in the same > ballpark.) > > And the mush-mellow methods like neural nets, excessive reliance on > logic, and excessive reliance on weighted reasoning do not impress me. > I am surprised by how much researchers have gotten out of them. I mean > wow! > > If I am not a logic-based AGI yahoo then why am I so interested in SAT > in p? Because the advance would be so powerful that it could be used > to advance a range of complex computational methods including AGI. > Jim Bromer > > > On Wed, Dec 2, 2015 at 1:43 PM, Jim Bromer <[email protected]> wrote: >> Stanley, >> Thank you for asking me these questions! I have thought about them. I >> want to respond over a few brief replies. The baby does not learn >> language by trying every possibility and a baby does need good sources >> to act as a guide in learning. (I mean I agree with those views.) But, >> how do you get that in a computer program? One of the most significant >> models of knowledge, (really the only one that I can imagine as >> viable) is a component model of knowledge. These component parts can >> be used in 'generating' different outputs. So we do not need to learn >> a separate name and symbol for every number, we can use 'components' >> to both represent them and to name them up to our limits of knowledge. >> But we only need to remember maybe a hundred different labels and how >> to attach them and we can thereby represent and talk about (samples) >> of octodecillions of numbers (if you can find the right page on >> Wikipedia to get the names of large numbers). >> But, you still have to follow certain rules when using one of those >> numbers. These rules are themselves expressed in the n-ary system as >> compressions that are convenient to use with many large numbers. (It >> is not convenient for us to do calculations on numbers in the >> octodecillion range but it is convenient for a computer to do >> calculations on numbers that large.) >> >> Some methods, like neural networks tend to combine the components 'of >> knowledge' but the successes in the field seem to reflect somewhat >> narrow AI applications. In other words the more interesting uses in AI >> are when they are treated more like component methods. My argument >> against them is that important knowledge (knowledge-stuff) is lost >> when you methodically trash or mush the component representations of >> that knowledge. >> >> However, there is no evidence -as of yet- that general knowledge can >> be so conveniently broken down to a convenient number of components as >> it has been done with the n-ary representations of numbers. So even >> though our would be AGI programs would use component models of >> knowledge it still would have to be able to go through heaps of stuff >> in order to find the best responses for a given situation. >> >> In a simple world model an AGI program could do deep searches without >> any problem. But as the world model becomes more and more nuanced the >> deep searches would *themselves* become nuanced just because they too >> are based on component models. The problem is that their are no >> conveniently compressed component methods that can be used on general >> AI. >> >> Imagination gives us the ability to think outside the box. It is at >> the least an ingredient of the 'magic sauce'. Once you begin to think >> deeply about reinforcement methods that are operating on an >> imaginative AGI program you will find that the simplicity of the >> method would start failing rather quickly at the least sign of >> conceptual complexity. >> Jim Bromer >> >> >> On Wed, Dec 2, 2015 at 11:35 AM, Stanley Nilsen <[email protected]> >> wrote: >>> Greetings Jim, >>> Have some questions and comments about the recent email... >>> (thread used to be: Scholarpedia article on AGI published) >>> >>> On generating possibilities... >>> >>> Complexity seems to be the issue that lies underneath much of your >>> efforts. And, there is no doubt that life has it's complexity. I don't >>> recall (didn't search past emails) any explanation from you, that ties this >>> complexity to an AGI implementation. >>> >>> I personally have an issue with complexity and that is because it is >>> over-rated. In many writings there is an implication that AGI type >>> intelligence will emerge through the construction of a unit that will try >>> lots of things and get feedback and thereby learn what creates the best >>> reward. Sort of an evolutionary intelligence. Do we really believe that? >>> I don't, do you? >>> >>> I've seen reference to "search space" and the implication is that the >>> intelligent unit is going to find an efficient way to navigate this huge >>> space of possible "stuff." Am I off track in assuming that this may be the >>> connection with trying to discover the p=np solution? Thus enabling the >>> traversing this search space more efficiently. Is this how you see a better >>> intelligence created? >>> >>> Perhaps a simple example will suffice to see my contrasting view of the >>> development of intelligence. Consider a new born baby, or imagine you >>> create a computer baby that has a sound generating capability. One could >>> program the computer to generate random sounds and then watch for feedback >>> at the keyboard or through a listening device. Good luck with that. There >>> are several ways one might alter the experiment and produce suggestive >>> results. But, lets save time because we know that a human intelligence, the >>> baby, does not "simply" try lots of sounds and thereby become a speaking >>> person. Instead, the baby learns by lots of feedback and, importantly, by >>> mimicking the sounds that it hears. What does this prove? >>> >>> First, it shows that the baby isn't developing an intelligence by randomly >>> trying every combination. Rather, the baby is "adopting" behaviors that >>> produce positive feedback from the adult who is nurturing the baby. Enough >>> about babies... >>> >>> The computer intelligence will not evolve from nothing, far from it. It will >>> need a core set of behaviors to work with. "Thousands of different >>> approaches" could refer to the thousands of "cores" that are eventually >>> developed by different researchers. The core will be a big factor in how >>> the intelligent unit goes about acquiring behaviors to add to it's core. >>> And, as you might suppose, the unit will be influenced by it's surroundings, >>> the core isn't everything. >>> >>> To net it out... It isn't the "learning" by trial and error that is >>> significant, it is the adoption process that dwarfs the "scientific" >>> gathering of truth. The baby AGI doesn't need lots of experiments, it needs >>> good sources to guide it's adoption process. >>> >>> Stan >>> >>> On 12/02/2015 07:36 AM, Jim Bromer wrote: >>>> >>>> ... >>>> >>>> It was useful to me only because it showed me how I might generate >>>> variations on the abstractions underlying some purpose. So my methodology >>>> might be used in an actual AI program to generate possibilities, or more >>>> precisely, generate the basis's for the possibilities. It would not stand >>>> as >>>> a basis for AI itself. Solomonoff's methods do not stand as a basis for AI. >>>> (Years from now, when there are thousands of different approaches to AI and >>>> AGI we might still disagree about this.) But it should be clear that I am >>>> saying that Solomonoff's universal prediction methods are not actually >>>> standards for viable AI. Compression methods are not a viable basis for AI >>>> either. They could be used as part of the process but it is pretty far >>>> fetched to say that any computational technique that could be used in an AI >>>> or AGI program could be used as a basis for AI. >>>> I just wanted to follow through since you wrote a reasonable reply to my >>>> first reply. >>>> >>>> >>> >>> >>> >>> ------------------------------------------- >>> AGI >>> Archives: https://www.listbox.com/member/archive/303/=now >>> RSS Feed: https://www.listbox.com/member/archive/rss/303/24379807-653794b5 >>> Modify Your Subscription: >>> https://www.listbox.com/member/?&; >>> Powered by Listbox: http://www.listbox.com ------------------------------------------- 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
