On Thu, Apr 4, 2013 at 7:02 PM, Mike Tintner <[email protected]>wrote:
The main task ...is to recognize how those objects *connect*, including "object mechanics." Who or what is doing what to who or what? ... Is the book lying on the box, or stuck to it? Are the flowers bending because of a wind or what? Is that a mess, or an orderly array of papers? "Object mechanics" includes how objects keep moving. Where will that moving object end up? Will he walk straight into the guy ahead? Will that ball hit the window, or will he have time to catch it first? ... The main task of vision/common sense/consciousness is to understand the *object connectivity* and *mechanics* of the agent's world. For living agents, the relevant objects and mechanics of the world to be analysed, increase in complexity with the complexity of the agent's body and mind, and therefore capacity to interact with the world. (So start your AGI at worm or simpler level not human level). ------------------------ If you start your AGI project with some kind of well defined intention agenda in mind it might be easier to get the project going. (This is important because the best way (the only way?) to write a complicated program is to start with something simple then keep on improving it.) With some narrow agenda you might be able to write an effective AGI program that is capable of meeting the agenda. Then, as you add to the agenda, if your basic concept was truly general and scalable you might be able to repeatedly improve on the program enough to show genuine advancement. However, if your idea is inadequate then you will get stuck pretty quickly. Our trouble defining the mechanisms of understanding shows that the agenda that we want to design is too broad and ill-defined. So instead of asking how can our program gain understanding we probably should ask how could our program deal with this kind of problem or that kind of problem where the mechanisms to deal with the problem are general and challenging but not undefinable. Then keep on going and see what happens. If your basic ideas are good, you will keep making progress. Jim Bromer On Thu, Apr 4, 2013 at 7:02 PM, Mike Tintner <[email protected]>wrote: > You're assuming that vision is mainly about object recognition. That's > still mindblowingly difficult, but relatively easy compared to the main > task of vision. > > The main task is not to recognize the objects in a scene - it is to > recognize how those objects *connect*, including "object mechanics." Who or > what is doing what to who or what? Did this guy fall because that guy > punched him or because he stumbled? Is the chair supporting him, or is he > squatting just over it? Is the book lying on the box, or stuck to it? Are > the flowers bending because of a wind or what? Is that a mess, or an > orderly array of papers? > > "Object mechanics" includes how objects keep moving. Where will that > moving object end up? Will he walk straight into the guy ahead? Will that > ball hit the window, or will he have time to catch it first? > > And so on and on. > > The main task of vision/common sense/consciousness is to understand the > *object connectivity* and *mechanics* of the agent's world. For living > agents, the relevant objects and mechanics of the world to be analysed, > increase in complexity with the complexity of the agent's body and mind, > and therefore capacity to interact with the world. (So start your AGI at > worm or simpler level not human level). > > P.S. One should add that present scientists and technologists are > *extremely* ill-equipped to deal with human or animal vision from any AGI > perspective. They are totally conditioned to think and look analytically in > considering any visual scene. They are conditioned by the > sentential/propositional form of logic, maths and language. They think in > terms of CAT ... SAT ... MAT. They don't even realise that > the reality being referred to here is not a set of building blocks, but a > movie of an object/animal moving continuously through a complex scene. They > don't have the artistic/ synthetic sensibility which looks at scenes as > wholes. They will have to acquire it. When humans look at scenes, we look > as both analytic scientists and synthetic artists. > > > > > > > > > > -----Original Message----- From: Matt Mahoney > Sent: Thursday, April 04, 2013 11:25 PM > To: AGI > Subject: Complexity of vision (was Re: [agi] Utilizing kickstarter.com?) > > On Wed, Apr 3, 2013 at 12:11 PM, Ben Goertzel <[email protected]> wrote: > >> By using more efficient algorithms than the human brain does ... >>>> >>> >>> How do you know that such algorithms exist? How do you calculate the >>> complexity? >>> >>> >> What matters is the average case complexity, relative to the >> probability distributions characterizing the actual environments and >> goals relevant to the AGI system... >> >> There is no good math for calculating this kind of complexity... >> >> So, we are relying in significant part on intuition here.... >> > > Turing's intuition was that computers were already fast enough to > solve AI. This was before vacuum tube computers like ENIAC, so I > presume he meant mechanical relays. > > Anyway, I would like opinions on the computational complexity of human > vision. Specifically, how would you optimize Google's cat face > recognizer and bring it up to human level? > http://128.84.158.119/abs/**1112.6209v3<http://128.84.158.119/abs/1112.6209v3> > > Their current implementation is a 9 layer neural network with 10^9 > connections. It was trained on 10^7 256x256 grayscale images for 3 > days on 16,000 CPU cores. It is 15.8% accurate on ImageNet, 70% better > than any other system. Presumably, humans would be able to recognize > most of the images. > > Google's system recognizes only still images in isolation. To bring it > to human level, it would have to model motion, color, and stereoscopic > depth perception. It would have a fovea and model saccades, for > example, scanning important visual features such as corners, faces, > words, and moving objects. It would have to be integrated with other > senses to aid recognition. For example, when you turn your head, the > model should predict how the image will change and extract features > from the residual errors. Vision makes heavy use of context. For > example, you can more easily recognize a co-worker at work than at the > store. > > By adulthood we see the equivalent of 10^10 images at a frame rate of > around 10 per second. Each frame has 10^8 pixels, although to be fair, > this is reduced to 10^6 low-level features by the retina. A single > processor running at 10^10 OPS could easily do this. It is harder to > estimate the number of higher level features processed by the (much > larger) visual cortex, such as lines, edges, and movement, and then > going up the hierarchy, corners, letters, words, faces, and familiar > objects. The number of top level features would be at least as large > as our vocabulary, about 10^5, although it is probably much higher or > else we could adequately use words to convey pictures. > > Google's system is trained on 10^11 bits. The optic nerve transmits > 10^16 bits by adulthood, or 10^5 times as much. Coincidentally, our > brain has 10^5 times as many synapses (10^14) as Google's model. We > don't need 10^5 times as many processors because the computation is > spread out over decades, rather than 3 days. I estimate 10^6 cores at > 10^9 to 10^10 OPS each. > > Is it possible to solve the problem with less hardware? How? > > -- > -- Matt Mahoney, [email protected] > > > ------------------------------**------------- > AGI > Archives: > https://www.listbox.com/**member/archive/303/=now<https://www.listbox.com/member/archive/303/=now> > RSS Feed: https://www.listbox.com/**member/archive/rss/303/** > 6952829-59a2eca5<https://www.listbox.com/member/archive/rss/303/6952829-59a2eca5> > Modify Your Subscription: > https://www.listbox.com/**member/?&;<https://www.listbox.com/member/?&;> > Powered by Listbox: http://www.listbox.com > > > ------------------------------**------------- > AGI > Archives: > https://www.listbox.com/**member/archive/303/=now<https://www.listbox.com/member/archive/303/=now> > RSS Feed: https://www.listbox.com/**member/archive/rss/303/** > 10561250-470149cf<https://www.listbox.com/member/archive/rss/303/10561250-470149cf> > Modify Your Subscription: https://www.listbox.com/** > member/?&id_**secret=10561250-b8cb8eb9<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
