This puts me in mind of something I read a while back (too long ago to have a link handy) where the language itself was evolved in a Genetic Programming algorithm. If a system dynamically evolved pieces of the language on-line, keeping constructs that improved the efficacy of the language, it could incrementally move the language towards the optimum without having to rewrite the entire knowledge base in terms of a brand new language, instead only rewriting those portions which are expressed in terms of constructs that are slated to be retired. The real difficulty would be in determining which language constructs were actually better than the others. I suppose if a certain amount of redundancy were built in to the system, so that knowledge is always represented by several different expressions using different language constructs, it would be possible to measure the relative compactness of the different forms and use that to measure the effectiveness of the participating constructs.
On Mon, Aug 27, 2012 at 12:18 PM, Ben Goertzel <[email protected]> wrote: > Yes, the iteration you mention is important... so at each stage in its > life, the AGI is doing Occam's Razor according to the "programming > language" implicit in what it's learned so far... > > This is a matter of learning "computational models / programming > languages" on the fly, that are specifically adapted to the > environment of a given intelligent system, and the internal structures > emergent within that system as it learns/grows/develops... > > And it may be that the "base", the initial measure of simplicity used > at the start of this iteration, is not all that relevant to the end > result -- so long as the base is something reasonable, and not totally > out of synch with the environment, goals and architecture of the > system... > > However, that doesn't eliminate the > theoretical/mathematical/philosophical question I posted in that blog > post... > > Please note: I don't think that theoretical/mathematical/philosophical > question needs to be solved in order to create AGI. OpenCog already > embodies its own choice regarding the base language for measuring > simplicity, the Atom language... > > I just think it's an interesting question, anyway... > > And it may be relevant ultimately to creating a good general theory of > general intelligence, which we lack now... > > However, I strongly suspect we can succeed at building powerful AGI > without needing to have a good general theory of general intelligence > beforehand.. > > ben > > > On Mon, Aug 27, 2012 at 12:37 PM, Boris Kazachenko <[email protected]> > wrote: > >> Just some speculations about possible theoretical computer science I'd > >> do if I had the time ;p > >> > >> > >> > http://multiverseaccordingtoben.blogspot.com/2012/08/finding-right-computational-model-to.html > > > > > > Maybe you should spend your time more wisely :). > > > > All this confusion results from using languages designed for irrelevant > > tasks. For GI, the language must be generated by the compressive Occam's > > Razor algorithm itself, with incremental syntax produced by its past > > iterations. Notice the POV difference: you don't have some fixed & final > > complexity for GI to reduce. Rather, you go through indefinite number of > > complexity accumulation / compression cycles. In my terms, that's a > > current-level search / next-level evaluation cycle, iterated for as long > as > > you keep accumulating the data. > > > > > > ------------------------------------------- > > AGI > > Archives: https://www.listbox.com/member/archive/303/=now > > RSS Feed: https://www.listbox.com/member/archive/rss/303/212726-11ac2389 > > Modify Your Subscription: > > https://www.listbox.com/member/?&; > > Powered by Listbox: http://www.listbox.com > > > > -- > Ben Goertzel, PhD > http://goertzel.org > > "My humanity is a constant self-overcoming" -- Friedrich Nietzsche > > > ------------------------------------------- > AGI > Archives: https://www.listbox.com/member/archive/303/=now > RSS Feed: https://www.listbox.com/member/archive/rss/303/23050605-bcb45fb4 > 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-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
