Abram Demski wrote below: "If the network is passing down an expectation based on other data, informing the lower network of what to expect, then this is forward chaining. But if the signal is not an expectation, but more like a query "pay attention to data that might conform/contradict this hypothesis, and notify me ASAP" then it is backwards chaining. And it seems realistic that it can be both of these."
This is interesting. The type of activation you claim would be backward chaining in this above quote corresponds to the "?" activation described in Shasti's Shruiti (which I have cited earlier in this thread). In Shruite any node that receives "?" activation spreads similar activation to other nodes that that might supply feedback to it that might provide evidence of an increase or decrease in probability of the asking node. But receiving "?" activation by itself does not change a nodes probability at all. Interestingly increasing or decreasing a nodes activation tends to spread "?" activation seeking feedback on whether the increased or decrease in probability is supported or contradicted by other information in the network. Ed Porter -----Original Message----- From: Abram Demski [mailto:[EMAIL PROTECTED] Sent: Monday, July 14, 2008 2:29 PM To: agi@v2.listbox.com Subject: Re: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE BINDING PROBLEM"? Ed Porter wrote: "I am I correct that you are implying the distinction is independent of direction, but instead is something like this: forward chaining infers from information you have to implications you don't yet have, and backward chaining infers from patterns you are interested in to ones that might either imply or negate them, or which they themselves might imply or negate." "BY READING BOTH THE WIKIPEDIA ENTRIES FOR FORWARD AND BACKWARD CHAINING AND READING ABRAM DEMSKI'S LAST POST, IT SEEMS THAT ONE OF THE DISTINCTIONS COMMONLY GIVEN BETWEEN FORWARD AND BACKWARD CHAINING, IS WHETHER ONE IS REASONING FROM DATA (IN THE CASE OF FORWARD CHAINING) OR FROM GOALS OR HYPOTHESES (IN THE CASE OF BACKWARD CHAINING)." As I understand it, this is the proper definition. The reason it is typically stated in terms of direction of inference over if/then statements is because that is how it is implemented in rule-based systems. However, reasoning from goals vs reasoning from data is the more general definition. Ed Porter also wrote: "For example, evidence may be derived from sensation, memory, cognition or other means that a certain high level pattern should exist in roughly a certain time and place, and the top down levels implication of what is should expect to see could be considered forward chaining, but is could also be considered backward chaining." Perhaps there is some real ambiguity here, arising from the probabilistic setting. If the network is passing down an expectation based on other data, informing the lower network of what to expect, then this is forward chaining. But if the signal is not an expectation, but more like a query "pay attention to data that might conform/contradict this hypothesis, and notify me ASAP" then it is backwards chaining. And it seems realistic that it can be both of these. On Mon, Jul 14, 2008 at 1:43 PM, Ed Porter <[EMAIL PROTECTED]> wrote: > > With regard to your comments below, I don't think you have to be too > imaginative to think of how the direction of forward or backward chaining > across at least certain sets of rules could be reversed. Abram Demski's > recent post gave an example of how both what he considers forward and > backward chaining can be performed in both directions across an inference > pattern. > > Plus, it should be noted that I never said all relationships involve a > before and after type of relationship. In fact, I specifically said some > relationships involve simultaneity. I do however think temporal > relationships are an important think to keep track of in inference, because > they are such and important part of reality, and predicting what is likely > to come next is such an important part of such reasoning, and reasoning > backward in imagined time from goals is such an important part of planning. > > BY READING BOTH THE WIKIPEDIA ENTRIES FOR FORWARD AND BACKWARD CHAINING AND > READING ABRAM DEMSKI'S LAST POST, IT SEEMS THAT ONE OF THE DISTINCTIONS > COMMONLY GIVEN BETWEEN FORWARD AND BACKWARD CHAINING, IS WHETHER ONE IS > REASONING FROM DATA (IN THE CASE OF FORWARD CHAINING) OR FROM GOALS OR > HYPOTHESES (IN THE CASE OF BACKWARD CHAINING). > > According to this definition the distinction between forward and backward > chaining is not about direction the inference travels though an inference > network --- because as Abram show each can travel in both directions --- but > rather the purpose for which the inference is being performed. According to > this definition, both bottom up and top down inference could each in certain > cases be considered both forward and backward chaining. > > This definition is probably more meaningful in an AGI context than having > the direction depend on which is the if clause and which is the then clause, > because in an AGI many of the rules would have been learned automatically > from correlations and there is often no reason to decide which of the > patterns that implies the other is the if clause pattern and which is the > then clause pattern. > > But this definition of the distinction as depending on whether one is > reasoning from data on one hand or goal and hypotheses on the other, is > confused by the fact that both Wikipedia articles implying forward chaining > is from if clause to then clause, and the reverse for backward chaining. > > It is also confused by the fact that in AGIs the distinction between data, > evidence, probability, attention, and hypothesis are not always clear. For > example, bottom-up feed forward inference from sensory input is often > considered to create perception hypotheses up the perception pathway, and > implication could be considered to be proceeding in a forward chaining way > from such each of such hypothesis. > > For example, evidence may be derived from sensation, memory, cognition or > other means that a certain high level pattern should exist in roughly a > certain time and place, and the top down levels implication of what is > should expect to see could be considered forward chaining, but is could also > be considered backward chaining. > > So I still find even this definition of forward and backward chaining would > be less than totally clear when applied in many possible situations in an > AGI. But many definitions that are used every day are less than totally > clear. > > Richard, you said below "If I had a penny for every time you have accused me > of being wrong, when later discussion showed that I was quite correct, I'd > have enough money to build an AGI tomorrow." > > Yea, Richard, an AGI about about as powerful as the typical Phantom Decoder > Ring you are likely to be able to purchase for one or two cents from the > back of a comic book. > > If however the same rule were applied to me, I would be able to buy an AGI > as powerful as Phantom Decoder Ring worth at least a buck. > > Ed Porter > > -----Original Message----- > From: Richard Loosemore [mailto:[EMAIL PROTECTED] > Sent: Monday, July 14, 2008 11:54 AM > To: agi@v2.listbox.com > Subject: Re: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY "THE > BINDING PROBLEM"? > > Ed Porter wrote: >> Richard, >> >> You just keep digging yourself in deeper. >> >> Look at the original email in which you said "This is not correct." The >> only quoted text that precedes it is quoted from me. So why are you > saying >> "Jim's statement was a misunderstanding"? > > Okay, looks like some confusion here: the structure of Jim's message > was such that I thought the relevant comment came from him. Turns out > he was just quoting you. That's fine (sorry Jim): it just means that > you made the misleading statement. > >> Furthermore, I think your criticisms of my statements are generally >> unfounded. >> >> My choice of the word "reasoning" was not "not correct", as you imply, > since >> the Wikipedia definition says "Forward chaining is one of the two main >> methods of REASONING when using inference rules." (Emphasis added.) > > That is fair enough. I think it is a matter of taste, to some extent, > but I will take the rap for going against the Wikipedia gospel. > > >> My statement made it clear I was describing the forward direction as being >> from the if clause to the then clause, which matches the Wikipedia >> definition, so what is "not correct" about that. > > I did not say that this part of the text was incorrect. > > >> In addition, you said my statement that in the absence of a temporal >> criteria "the notion of what is forward and backward chaining might be >> somewhat arbitrary" was a "completely incorrect conclusion." >> >> Offensively strong language, considering it is unfounded. > > Or, if it should turn out that it was well-founded, it would have been > quite polite and matter-of-fact to say "completely incorrect" > > >> >> It is unfounded because in the absence of a temporal distinction, many >> if-then rules, particularly if they are probabilistic, can viewed in a two >> way form, with a probabilistic inference going both ways. In this case it >> becomes unclear which side is the "if" clause, and which the "then" > clause, >> and, thus, unclear which way is forward and which backward by the > definition >> contained in Wikipedia --- unless there is a temporal criteria. This > issue >> becomes even more problematic when dealing with patterns based on temporal >> simultaneity, as in much of object recognition, in which even a temporal >> distinction, does not distinguish between what should be consider the if >> clause and what should be considered the then clause. > > Here is an example of backward chaining: > > Start with a question: Is it true that "Socrates is mortal"? > > Start by looking for any knowledge that allows us to conclude that > anything is or is not mortal. We search the KB and come up with these > candidates: > > "If x is a plant, then x is mortal" > "If x is a rock, then x is not mortal" > "If x is a robot, then x is not mortal" > "If x lives in a post-singularity era, then x is not mortal" > "If x is a slug, then x is mortal" > "If x is a japanese beetle, then x is mortal" > "If x is a side of beef, then x is mortal" > "If x is a screwdriver, then x is not mortal" > "If x is a god, then x is not mortal" > "If x is a living creature, then x is mortal" > "If x is a goat, then x is mortal" > "If x is a parrot in a Dead Parrot Sketch, then x is mortal" > > Now, before we go on to look at the second stage of this backward > chaining example, could you perhaps explain to me how "the absence of a > temporal distinction" applies or does not apply to any of these? I do > not believe that it is possible to reverse any of these rules, temporal > distinctions or any other distinctions.... you cannot say "if x is > mortal, then x is a plant", nor "if x is not mortal, then x lives in a > post-singularity era", etc etc etc. > > In the process of backward chaining, the next step is to see if the > antecedents of any of these might allow us to connect up with Socrates > in some way, so we start with the first one, "If x is a plant" and try > to find out if anything allows us to conclude that Socrates is or is not > a plant. A search of the KB turns up these statements: > > "If x contains chlorophyll, then x is a plant" > "If x is a dandelion, then x is a plant" > ..... and on and on and on. > > A couple of years later, after going several levels deep in its search, > the system finally digs deep enough in its knowledge base to come up > with the following chain of inference: > > "Socrates contains blood" > "If x contains blood, then x will bleed when pricked" > "If x bleeds when pricked, then x is a man" > "If x is a man, then x owns footwear" > "If x owns footwear, then x is a living creature" > "If x is a living creature, then x is mortal" > > > And now, FINALLY, the backward chaining mechanism will be able to > conclude that "Socrates is mortal" > > Please, Ed, could you explain to me how this typical case of backward > chaining could be reversed so that it becomes just a variation on > forward chaining? > > The two mechanisms simply have different properties. If you were to try > to prove "Socrates is Mortal" by forward chaining, what would you do? > Start from a random point in your KB and start proving facts in random > order? How would you use the reversibility of the rules, which you > claim to exist, to set up a forward chaining proof, instead of using > backward chaining? > > If there is no practical way to substitute forward chaining for backward > chaining, in what sense would it be true that one was just a kind of > variation on the other? > > Hey, if I am wrong, I would love to hear some more about it, because I > will have learned something. So far, I have just been quoting the > established understanding of the meaning of these terms and wondering > why I, personally, am taking so much heat for it. > > >> Enough of arguing about arguing. You can have the last say if you want. > I >> want to spend what time I have to spend on this list conversing with > people >> who are more concerned about truth than trying to sound like they know > more >> than others, particularly when they don't. >> >> Anyone who reads this thread will know who was being honest and reasonable >> and who was not. >> >> Ed Porter > > If I had a penny for every time you have accused me of being wrong, when > later discussion showed that I was quite correct, I'd have enough money > to build an AGI tomorrow. > > > > Richard Loosemore > > > P.S. You know, it is interesting for me to ask myself "Why do you > correct people on the AGI list when they say something that you think is > wrong? Why not just ignore it and let them be wrong?" I suppose the > main reason I do it is that if I stay quiet and just let the list > degenerate into a gang of people talking nonsense to one another, with > nobody stepping in to point out the more obvious errors, then this list > will have become completely worthless. > > > > > > > > > > > > ------------------------------------------- > 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/?&; > 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/ > 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/ 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/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=108809214-a0d121 Powered by Listbox: http://www.listbox.com
