Matt:
(Sorry about the delay... I was busy advertising in other groups..)
> But now that you have completed your theory on how to build AGI, what do you
> do next? Which parts will you write yourself and which parts will you
> contract out?
> do next? Which parts will you write yourself and which parts will you
> contract out?
Ideally, any part that can be "out-sourced" should be out-sourced.
At this stage let's see who are interested in this approach...?
> I still think there are still some fundamental problems to be solved. Your
> system is based on first order logic. (You said that is not a fixed design
> feature, but without a data structure you don't have a design). I am not
> aware of any system that has successfully integrated FOL (or its augmented
> variants) with sensory/motor data or language.
For sensory processing, I think the main reason is that FOL is not probabilistic. We need to combine probability with FOL, which is not that hard. A Bayesian network can be viewed as propositional logic + probability.
For natural language, perhaps the reason is that they have only focused on inference and ignored pattern recognition, which, as I argued, is the basis of dealing with the semantics of words.
> All such systems require
> human programmers to explicity encode knowledge. You have many examples of
> how various types of knowledge can be represented. Books and papers on
> knowledge representation are full of similar examples. What these examples
> all lack is an explicit algorithm for acquiring such knowledge. Sure,
> humans can do it easily, but if you make your learning mechanism this smart,
> then you have already solved AGI. If it took anything less than human
> knowledge to do it, then surely systems like Cyc would have been built this
> way. Why spend 20 years hand coding millions of rules instead of a few days
> crunching a terabyte of text off the Internet?
> human programmers to explicity encode knowledge. You have many examples of
> how various types of knowledge can be represented. Books and papers on
> knowledge representation are full of similar examples. What these examples
> all lack is an explicit algorithm for acquiring such knowledge. Sure,
> humans can do it easily, but if you make your learning mechanism this smart,
> then you have already solved AGI. If it took anything less than human
> knowledge to do it, then surely systems like Cyc would have been built this
> way. Why spend 20 years hand coding millions of rules instead of a few days
> crunching a terabyte of text off the Internet?
I think there is no shortcut to knowledge acquisition. Doug Lanet has argued that much of common sense knowledge is missing from the internet. For example a Google search of "water flowing downhill" returns 987 hits versus 1480 hits for "water flowing uphill". He argued that adult speech
assumes common sense knowledge and thus is a bad source of common sense.
There are multiple reasons why Cyc is not yet successful -- lack of sensory input (vision), not good enough to converse in natural language, inference engine not advanced enough, no probabilities or fuzzy logic, etc. It's like the failure of early gliders to fly, which doesn't mean that flying with planes is impossible.
> Successful language models like Google are based on statistical models, not
> FOL. Likewise, successful applications in vision or robotics generally use
> numerical/signal processing/neural models.
A FOL formula such as "Sexy(x) ^ Intelligent(x)" is not unlike a neuron that detects 2 weighted inputs. If you add probabilities to FOL then they are even more similar.
But logic is more powerful because it can use variables. For example "Kicks(x,y)" is very VERY difficult to be expressed by statistical models or NNs, because it has to match "John kicks Mary" and "boy kicks dog", "robot kicks ball", etc.
> I think to succeed at AGI, we need to understand the theoretical limits of
> learning [1,2], then develop a system not based on methods that have already
> been shown not to work. Then build a system that can learn, give it enough
> raw data to do so, and set it loose.
First of all we got to have a wine cup that is capable of holding the wine (knowledge). In other words, we need an architecture that can at least do inference, pattern recognition, planning, etc,
sans knowledge. This I claim is G0.
Then we need to fill the cup with wine, and it is here that involves learning. Yes, I am aware of the theoretical limits of learning. The real challenge is finding the heuristics. Learning in AGI is hard because the training set (= all of episodic memory) is huge. My guess is we can use stochastic algorithms to tackle this -- I heard that they are pretty good at dealing with NP-hard problems.
YKY
This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
