How exactly do you suggest to bridge the functionality gap between visual pattern recognition and all the other things human beings do?
On Thu, Jun 28, 2012 at 12:19 PM, Alan Grimes <[email protected]> wrote: > I'm sorry, I've been too busy recovering from a 2-day internet outage to > notice this gem of an article. There are some moderately deep problems > with the approach proposed here. There are some serious theoretical > challenges yet outstanding but this is precisely what a solution to AGI > will look like. I mean these d00dz have the tiger by the tail. Vector > based pattern matchers, as I've argued before, are inherently limited > but if this can be made to ignore the position and angle of the > stimulus, or treat it separately, the problem is $01V3D. The only thing > left to do after that is to organize it into a complete cybernetic > system with sufficient capacity and you're D0N3. (yeah, there are a few > other issues that might turn out to be thorny, but basically...) > > AGI is now just a question of money and willpower. =P > > > Matt Mahoney wrote: >> On Wed, Jun 27, 2012 at 2:09 AM, bfrs <[email protected]> wrote: >>> nytimes article on this paper: >>> https://www.nytimes.com/2012/06/26/technology/in-a-big-network-of-computers-evidence-of-machine-learning.html?_r=1 > >> Original paper here: >> http://arxiv.org/pdf/1112.6209v3.pdf > >> To summarize, a 9 layer neural network with 10^9 connections is >> trained unsupervised for 3 days on 1000 16-core CPUs on 10^7 unlabeled >> 200x200 images, each a random frame from a different Youtube video. >> When the resulting top level neurons are examined, it turns out that >> there are detectors for (among other things) human faces, human >> bodies, and cats. > >> It was not told to look for these things. This is just a compression >> problem. If you want to encode an image efficiently, then you do so by >> describing its high level features (e.g. a person holding a cat). The >> learning problem is to find a set of useful features, knowing nothing >> about the world or what these arrays of pixels might represent. > >> It does not achieve human level accuracy, but is still better than >> anything else. The equivalent problem for human vision would be to >> train 10^13 synapses for a decade on 10^9 images of 10^8 pixels each. > > > -- > E T F > N H E > D E D > > Powers are not rights. > > > > > > ------------------------------------------- > 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/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
