EFTA01793461.pdf

From: Joi Ito Sent: Tuesday, October 22, 2013 11:27 AM To: Epstein Jeffrey Subject: Re: MDF Attachments: signature.asc Sorry, not brain. Cog Sci and Al. On Oct 22, 2013, at 07:26 , Joi It rote: > BTW, getting going with Joscha. He's smart. Let me know if you're =nterested in joining the brain threads. > Begin forwarded message: » From: Joscha Bach » Subject: Re: MDF » Date: October 21, 2013 23:56:09 -0400 » To: Joi Ito » Cc: takashi ikegami Ari Gesher Kevin Slavin Martin Nowak reg Borenstein » Hi Takashi, hi An, hi all, » finally I got around to look at Takashi's talks and his 2010 ACM =rticle. The first thing that came to mind was the distinction between =neat" and "scruffy" Al, which might be described as the clash between =olks that wanted to construct Al by adding function after function, vs. =hose that want to take a massively complex system and constrain it =ntil it only does what it is supposed to do. >> » The idea of starting from massive data flows is very natural and =heoretically acknowledged, even it is often practically neglected. =ognition, by and large, is an organism's attempt to massively reduce =omplexity, by compressing, encoding, selectively ignoring, abstracting, =redicting. controlling it. Thus, it seems natural to focus on the =echanisms that handle this complexity reduction, which I think is =xactly what most research in computer vision, machine learning, =lassification, robot control etc. is doing. A lot of the work on =roblem solving and learning within cognitive science even works _only_ =n the highest level of abstraction, i.e. grammatical language, regular =oncept structures, ontologies and soon. >> » If I understand Takashi correctly, he points towards another » =erspective: (please forgive and correct me if I should oversimplify too =uch here) 1. Cognitive systems do not only need to reduce complexity, but also =uild it (for instance, take simple cues or abstract input and use it to =eed a rich, heterogenous, ambiguous and dynamic forest of =epresentations). » 2. Cognitive processes that work directly on and with high complexity =ata are under-explored. » 3. The study of systems that are immersed in such complexity might =pen the door to understanding intelligence and cognition. » There is really much more in Takashi's talk, but let me respond to =hese in turn: EFTA_R1_00126463 EFTA01793461 » 1. I believe that cognition is really about handling massive data =lows, by encoding it in ways that the cognitive agent can handle and =se to fulfill its demands. This works mostly by identifying apparent =egularities and turn them into perceptual categories, features, =bjects, concepts, ontologies and so on. Our nervous system offers =everal levels and layers of such complexity reduction, the first one of =ourse at the transition between sensory inputs and peripheral nervous =ystem (for physiological, tactile, proprioceptive input), or, in the =ase of visual perception, the compression we see between retina and =ptic nerve. The optic nerve transmits massively compressed data from =he retina to the thalamus, and from there to the striate cortex (the =rimary visual cortex, V1). V1 is the lowest level of a hierarchy of =isual and eventually semantic processing regions: from here, the dorsal =nd ventral processing streams head off into the rest of the cortex. V1 =ontains filtering mechanisms, which basically look for blobs, edges, =ovements, directions and soon, based on local contrasts. V2 organizes =hese basic features into a map of the visual field, including contours, =3 detects large, coherently moving patterns, V4 encodes simple =eometric shapes, VS seems to take care of moving objects, and V6 =elf-motion. The detection of high-level features always projects back =nto the lower levels, to anticipate and predict the lower level =eatures that should be isolated based on the higher-level perceptual =ypothesis. The story is similar for auditory processing, and eventually =he integration of basic visual and optical percepts into semantic =ontent: at each level, we take extremely rich and heterogeneous =atterns and reduce their complexity. » The transformation from concepts to language also represents another, =ncredible level of complexity reduction. » The highest complexity reduction, however, takes place at the =nterface between conscious thought and all the other processes. I =elieve that the prefrontal cortex basically holds a handful of pointers =nto the associative cortical representations, skimming off only a =andful objects, relations or features at a time, and bring them into =he conscious focus of attention. » The perspective of the need for staying at a complex level is =ntirely warranted, though: there are many intermediate representations =hat allow cognitive processes only if the complexity stays high, and =ight even need to increase it. This includes many sensor-motor =oordination processes, but also most creative, more intuitive =xploration. » This is not the same complexity as the one at the input, however! =his as a level where data is already split into modalities, =emantically organized and so on. On the other hand, it is much more =omplex as linguistic or cognitively accessible types of mental content. » 2. Scientists tend to have a fixation on thinking with language, and =t is quite natural to fall for abstract, a-modal representations, such =s predicate logic systems or extensions of these when it comes to =odeling cognition and problem solving. This might explain the fixation =f cognitive architectures like Act-R and Soar on rule-based =epresentations, and the similar approaches of a lot of work in =lassical Al. » On the other hand, there is a lot of work on learning and » =lassification to handle vast complexity, with the goal of reducing » it. =A particular beautiful example was Andrew Ngs work on deep » learning, =here his group took 30 million randomly chosen frames from » Youtube, and =rained an unsupervised neural net to make sense of » them. They ended up =ith spontaneously emerging detectors for many » typical object =ategories, including cats and human faces. I could » not avoid to think =f that paper when Takashi mentioned his » fascination with looking at TV =ixels directly...) --> » http://arxiv.org/pdf/1112.6209.pdf » Thus, the typical strategies seem to encompass "abstract 2 abstract" =ognition, and "complex 2 abstract" cognition. What about "abstract 2 =omplex" and "complex 2 complex"? Most of the existing approaches on =complex 2 complex" cognition are not really cognitive, such as Ansgar =redenfeld's "Dual Dynamics" architecture, or Herbert Jaeger's Echo =tate Networks. The current proponents of such complex cognition are =lso often radical embodimentalists (cognition as an extension of sensor =otor control, neglecting dreams, creativity, imagination, and =apabilities for abstract thinking). 2 EFTA_R1_00126464 EFTA01793462 » 3. The idea of getting to artificial intelligence _just_ by "looking » =t" (blind deep learning) on complex data flows is not new. I think that =here are at least two aspects to it: deriving a content structure that =flows the identification and exploitation of meaningful semantic =elationships (for instance, discerning space, color, texture, causal =rder, social structure, ... for instance simply by analyzing all of =outube, or by collecting data from a robotic body and camera in a =hysical world), and the integration of that structure with an =rchitecture that is capable of thought, language, intention, goal =irected action, decision making, and so on. The former is tricky, the =atter impossible. Complexity itself does not define intentional action, =nd the differences between individuals and species should not be =educed to differences in complexity perceived by the respective agents. =» I agree that we need to gain a much better understanding of "complex = complex" cognition, but that must integrate, not replace what we =lready know about the organization of cognitive processes. I am certain =hat our current models are a long way off from capturing the richness =f conscious experience of our inner processes, and even more so from =he much greater complexity of those processes that cannot be =xperienced. >> » Another interesting point I gathered from Takashi's talk is the idea =f something we might call "hyper-complex" cognition. The complexity =andled by our human minds (as well as the one of Andrew Ng's deep =earning Youtube watching networks) builds on very simple stimuli. But =hat if the atoms themselves are abstract or highly complex, for =nstance because they are already semantic internet content? The =ognitive agents handling those elements may essentially be operating at = level above human cognition if they are capable of operating on that =omplexity without reducing it. Unlike humans which are forced to =ranslate and reduce all content into their individual frame of =eference, and access it only through a single perspective at a time, =rtificial agents do not need to obey such restrictions. Today's Big =ata moniker probably marks just the beginnings of the abilities of =achines to make sense of abstract and complex input data. » Cheers, » Joscha >»» Fascinating. Ikegami is taking a very interesting tack: >>>» >»» http://www.youtube.com/watch?v=tOLIHhjNIFIc >»» http://sacral.c.u-tokyo.ac.jp/pdf/ikegami_ACM_2010.pdf >>>» >»» For me, this is similar to the discussions that you and I and =evin have been having about auto-didactism: starting from complexity =ather than abstraction (which is generally antithetical to academic =earning). It would seem to me that most artificial intelligence =esearch has started from abstraction (and forgive my ignorance if I'm =ff base here) and attempted to build up to complexity. My very cursory =ook at the Joscha's MicroPSl work seems to show an approach moving in =he direction of the what Ikegami did with the MTM from the classical =bstraction-first approach. MicroPSl places its constructs in a reduced =idelity virtual environment, has lower-level abstractions, and brain =tructures/dynamic pre-synthesized for things like motivation, emotion, =please correct me if I'm off base - like I said: cursory). The brain =tructures in living systems have have evolved as low-energy means of =rocessing brain signals (both sensory data flows and internally routed =creams) once they have showed fitness - ultimately, they were =and-blasted into their shape by generations of massive data flows. We =ave an understanding of what purpose they serve but not a good =nderstanding of how they work (maybe I'm behind on the state of the art =n neuroscience on that point?). >>>» >»» Ikegami is starting from the complexity and seeing what emerges - =hich seems to me to mirror the rise of consciousness in natural =ystems. Mind is the surfer that hangs on the eternal wave of the =assive data flow of sensory input without wiping out. Somehow, the =eality of the temporally continuous observer arose from exposure to =ensory 3 EFTA_R1_00126465 EFTA01793463 data flows and the evolution of the complexity of the brain. =kegami is shortcutting the snail's pace of the physical evolution of =atural systems by synthesizing a neural network of sufficient =omplexity as well as high-resolution sensors. >>>» >»» Thinking about modern synthetic data flows (you know.... the =nternet!) as being as rich as sensory data leads one to imagine some =nteresting possibilities in a) whimsically, the spontaneous emergence =f consciousness and b) practically, new techniques for dealing with =hat massive data flow that mimic something like natural consciousness. =here's nothing in the practical world of big data that really looks =ike the MTM (that anyone is talking about - who knows what lurks in the =igh frequency trading clusters busily humming in the carrier hotels). =verything that Google and Facebook and the like seems to be doing is =uch simpler than anything like this. >>>» >>>» >»» On Oct 19, 2013, at 9:37 AM, Joi Ito .c wrote: >>>» >>>>» >>»» http://www.dmi.unict.itiecal2013/workshops.phott4th-w >>>>» >>»» - Joi > Please use my alternative address, o avoid email > =uto responder Please use my alternative address o avoid email auto =esponder 4 EFTA_R1_00126466 EFTA01793464