Shane, I dealt with this in my 2006 book The Hidden Pattern by distinguishing [roughly speaking -- there was some formalism but I'll avoid it for the moment]
intelligence in context C = total complexity of goals achievable in C efficient intelligence = average over all goals G in C of: [achievability of G / resources needed to achieve G] According to this distinction, AIXI and evolution have high intelligence but low efficient intelligence. Pei's definition of intelligence really has to do with efficient intelligence, according to this distinction. The splitting of the NL word "intelligence" into more than one technical term is only natural since NL terms are ambiguous and technical terms need to be precise. My hypothesis is that the structures and dynamics required for achieving a high degree of efficient intelligence are FUNDAMENTALLY DIFFERENT FROM the ones required to achieve high intelligence and efficiency be damned. In the same sense (or perhaps even more strongly) that the ideas required to solve linear programming in polynomial time are fundamentally different from the ideas required to solve it in exponential time... or the ideas required to do sorting in nlogn time are fundamentally different from the ideas required to do sorting in n^2 time [Note: I am not arguing that intelligence is about getting algorithms with better orders of worst-case complexity. Actually I think it's about getting better average-case complexity where averages are weighted by appropriate probability distributions. I'm just making a rough analogy to a better-understood domain.] If this hypothesis is correct then AIXI and the like don't really tell us much about what matters, which is the achievement of efficient intelligence in relevant real-world contexts... -- Ben G On 5/17/07, Shane Legg <[EMAIL PROTECTED]> wrote:
Eliezer, > As the system is now solving the optimization problem in a much > > simpler way (brute force search), according to your perspective it > > has actually become less intelligent? > > It has become more powerful and less intelligent, in the same way that > natural selection is very powerful and extremely stupid. I think the best way to resolve this is to be more specific about what we are calling powerful or stupid. At a micro level an individual act of selection, reproduction etc. that evolution is built upon is not powerful and is extremely stupid. At a macro level when we consider an entire environment that performs trillions of trillions of acts of selection, reproduction etc. over billions of years, that system as a whole is very powerful, intelligent and creative. The same can be said of the brain. At a micro level an individual act of Hebbian learning etc. on a synapse is not very powerful and quite stupid. However, at a macro level when you consider trillions of trillions of these acts in a system that has been trained over a couple of decades, the result is the brain of an adult which is indeed powerful and intelligent. Shane ------------------------------ 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/?&;
----- 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/?member_id=231415&user_secret=fabd7936
