> > Suppose you have a simple predictor with Kolmogorov complexity N. Then > I can create a sequence with about the same complexity that your > predictor can't predict. My program simulates your program and outputs > the opposite of whatever you predict.
All you're really saying is, you can't predict everything. The universe can always surprise us, no matter how smart we are. That fact in itself is *not* a surprise. Your proof applies just as well to us as to any machines we create, but it isn't proving what you say it proves. Being right all the time isn't part of any definition of intelligence I have heard; learning from past mistakes is. Otherwise, we ourselves couldn't be considered intelligent. We start with relatively low complexity and incorporate it from our surroundings through experience, as is evidence by the enormous diversity of culture and knowledge we are able to handle with the same basic brain design. Every new experience is an incorporation of new complexity. I would expect you of all people to recognize that when we record memories or learn new skills, that encoding process does not come for free; our brains reorganize to store the new information, adding to our own behavioral algorithmic complexity. The universe, or at least the corner of it we live in, is highly patterned (i.e. highly compressible), based on what we have observed so far. Barring a surprise there of the very sort you describe, we can predict from past experience that it will continue to be so. In that case, a relatively simple program that observes, remembers, generalizes, and bases predictions on past observations could incorporate the complexity of its environment towards increasingly successful prediction. Sometimes it will be wrong, just like us, but that doesn't mean it won't be intelligent. On Tue, Feb 17, 2015 at 5:10 PM, Matt Mahoney via AGI <[email protected]> wrote: > On Tue, Feb 17, 2015 at 4:18 PM, Aaron Hosford <[email protected]> > wrote: > >> We can prove that good solutions must have high algorithmic complexity. > > > > Could you give a sketch for such a proof? > > Suppose you have a simple predictor with Kolmogorov complexity N. Then > I can create a sequence with about the same complexity that your > predictor can't predict. My program simulates your program and outputs > the opposite of whatever you predict. > > The long version by Legg: http://arxiv.org/abs/cs/0606070 > > > Why does the complexity have to > > initially reside in the algorithm, rather than in the environment? > > Because the environment can lie. I could give your predictor some code > that would make it a better predictor, or worse. It has no way to > know. > > And once it has collected all human knowledge, learning will slow down > because it will have to learn by experiment just like we do. Some > experiments take a long time no matter how smart you are. For example, > we know very little about what therapies will slow down aging. Any > experiment takes decades to get an answer. This is the reason that the > rate of increase of worldwide life expectancy peaked at 0.2 years per > year in the 1990's (1970's in developed countries) and is declining. > > And yes, we have machines that can go to the moon. They are stronger > and faster. They are also more intelligent, depending on what test you > use for intelligence. If the test is arithmetic speed and accuracy, > then machines surpassed human level intelligence 100 years ago. > > But again, intelligence is not the goal. > > -- > -- Matt Mahoney, [email protected] > > > ------------------------------------------- > AGI > Archives: https://www.listbox.com/member/archive/303/=now > RSS Feed: https://www.listbox.com/member/archive/rss/303/23050605-2da819ff > 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-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
