In the course of doing some research into A(G)I models I've found myself stuck on one conundrum. One of the core feautures of general intelligence seems to be something like domain-independent pattern finding - a truly *general* intelligence would be able to "suss things out" so to speak in a variety of different domains with roughly similiar efficacy.
The problem that strikes me here is something like the *pragmatic* (as opposed to epistemological) problem of induction. This being the issue of building a model that can intelligently (that is, better than brute force) extract patterns from raw data with little to no bias for its mode of presentation. After combing through some existing ideas (like Solomonoff induction and Hutter & Legg's universal intelligence), it seems like this may be impossible in principle. Because the optimal pattern that fits the given data would have length equal to the (incomputable) Kolmogorov complexity, intelligent induction with no prior schemas or patterns might be elusive. So Kant is vindicated in that intelligence cannot exist without some built-in schemas.
My question then is if anyone has come up with some kind of formal proof for this thesis or if it might just be obvious from the reasoning given above.
In the course of doing some research into A(G)I models I've found myself stuck on one conundrum. One of the core feautures of general intelligence seems to be something like domain-independent pattern finding - a truly *general* intelligence would be able to "suss things out" so to speak in a variety of different domains with roughly similiar efficacy.
The problem that strikes me here is something like the *pragmatic* (as opposed to epistemological) problem of induction. This being the issue of building a model that can intelligently (that is, better than brute force) extract patterns from raw data with little to no bias for its mode of presentation. After combing through some existing ideas (like Solomonoff induction and Hutter & Legg's universal intelligence), it seems like this may be impossible in principle. Because the optimal pattern that fits the given data would have length equal to the (incomputable) Kolmogorov complexity, intelligent induction with no prior schemas or patterns might be elusive. So Kant is vindicated in that intelligence cannot exist without some built-in schemas.
My question then is if anyone has come up with some kind of formal proof for this thesis or if it might just be obvious from the reasoning given above.