I don't think a single person is disputing this. - Dillon
-----Original Message----- From: nupic [mailto:[email protected]] On Behalf Of John Blackburn Sent: Wednesday, July 01, 2015 5:32 AM To: Dillon Bender Subject: Re: Response to Jeff Hawkins interview. To show that the brain is not a blank slate at birth consider Dan Dennet's famous "Robot Control Room" thought experiment. https://books.google.co.uk/books?id=9SduAwAAQBAJ&pg=PA102&lpg=PA102&dq=dan+dennett+room+with+buttons+no+labels&source=bl&ots=sn6r5623Ll&sig=4mWDStGDI9kO2j1ze2-VHcTmXGw&hl=en&sa=X&ei=t76TVdnNJYyq-AHJnb74Aw&ved=0CCUQ6AEwAA#v=onepage&q=dan%20dennett%20room%20with%20buttons%20no%20labels&f=false This shows that a working robot, based on HTM will need other stuff as well, some hard-wired stuff. Or it'll never be able to learn anything. On Wed, Jul 1, 2015 at 11:18 AM, John Blackburn <[email protected]> wrote: > I agree with this Matthew. It's important to remember how much of our > behaviour is hard wired into our brains due to evolution. Simpler > animals like ants have pretty much everything wired in at birth. > Despite their tiny brains (and no neocortex btw) ants are capable of > tasks like raft building and farming. If ants have so much pre-wiring > you can bet humans have much more. Until we understand how ants can > possibly do these tasks (in a very detailed neuron-by-neuron way) > we'll never by able to make an artificial insect. If we can't make an > insect, we can't make a mouse. If we can't make a mouse we have NO > HOPE at an artifical human! > > Trying to make a human brain in 2015 is like the Wright Brothers in > 1903 trying to make an A380 jumbo jet. They had to start small and > simple and slowly work up. Every plane they got to fly gave them > skills to develop the next model. The other thing about them is, when > they actually got a machine to fly, every layman could tell they had > succeeded! For Nupic it has to be the same. We have to eventually > produce something that any layman can appreciate is intelligent. In my > opinion it must therefore be embodied (virtual reality is OK too). So > the question: what is the ultimate goal of Nupic? How will we know we > succeeded? > > We can't just present an animation of active/inactive neurons on a > computer screen. Nor is a good fit to a time series enough. Even if we > assure people the algorithm is based on the human brain they will not > be impressed. That would be like the Wright brothers saying "well we > don't have a flying machine -- how vulgar! -- but look at these > wonderful equations we wrote! The problem of flight is solved!". No > it's got to be something real, which humans can tell is intelligent -- > which SCREAMS intelligent! > > My advice: an artifical ant which can pass the "ant Turing test", i.e. > with all the intelligence, responsiveness, intuition, survival > instinct etc of a real ant (possibly even accepted by the ant colony). > Don't underestimate how much effort this will take! > > On Tue, Jun 30, 2015 at 9:21 PM, Matthew Lohbihler > <[email protected]> wrote: >> The Helen Keller example is probably not appropriate since her >> intelligence was the result of an evolutionary process that expected >> inputs typical of an embodiment, and in the absence of a number of >> those developed itself with what input was available. I would say >> this only indicates how similar humans really are, not how an >> intelligence can develop from any old basis. Trying to create an >> intelligence that is not embodied the way John suggests might work in >> some fashion, but don't expect it to be able to understand or relate much to >> humanity. >> >> >> On 6/30/2015 3:40 PM, Julian Samaroo wrote: >> >> The body is really just the input and output systems that the neural >> structures attach to, as well as providing the ever-important task of >> supplying nutrients, fighting disease, etc. But in AI, it is simply >> abstracted away, and you are left with a set of sensory inputs and >> motor outputs, which can be anything you'd like. As David said, sight >> and audition aren't vital to intelligence in its most simplistic >> form, and you can thus attach something like HTM to any input-output >> pair that you can think up (although this doesn't necessarily imply anything >> useful will come of it). >> >> Julian Samaroo >> Manager of Information Technology >> BluePrint Pathways, LLC >> (516) 993-1150 >> >> On Tue, Jun 30, 2015 at 2:36 PM, cogmission (David Ray) >> <[email protected]> wrote: >>> >>> John, >>> >>> I just thought of this. I wonder how relevant the experiences of >>> sensory deprived individuals are to a comparison of the capabilities >>> of "dis-embodied" intelligences? Someone like Helen Keller who maybe >>> only had kinesthetic and taste senses, could maybe be analogous in >>> some way to a developing dis-embodied intelligence? Maybe not, just a >>> thought... >>> >>> On Tue, Jun 30, 2015 at 2:21 PM, Matthew Taylor <[email protected]> wrote: >>>> >>>> John, >>>> >>>> Just to make sure that all your questions have been addressed directly: >>>> >>>> On Tue, Jun 30, 2015 at 2:55 AM, John Blackburn >>>> <[email protected]> wrote: >>>> > "performs with true intelligence" is a pretty bold claim. If this >>>> > is the case, how come there are no very convincing examples of >>>> > HTM working with human like intelligence? The Hotgym example is >>>> > nice but it is really no better than what could be achieved with >>>> > many existing neural networks. Echo state networks have been >>>> > around for years and can make temporal predictions quite well. >>>> >>>> People define "intelligence" in different ways. If you take for >>>> granted that the neocortex has "true intelligence", then HTM might >>>> be called an implementation of "true intelligence" algorithms based >>>> upon the fact that it acts upon incoming data with the same basic >>>> principles as the neocortex. We are trying to lift the intelligence >>>> out of the brain and into software, one step at a time. >>>> >>>> So, while NuPIC's performance might not seem all that impressive >>>> when other technologies can do similar things, we have lots of room >>>> to grow [1] and a lot more work to do. All of this upcoming work >>>> should increase the capabilities of the HTM system we are >>>> implementing. The fact that we are somewhat on-par with some other >>>> ML techniques at this point is encouraging to me. >>>> >>>> > I recently presented some >>>> > time sequence data relating to a bridge to this forum but HTM did >>>> > not succeed in modelling this (ESNs worked much better). >>>> >>>> I had a little time to work on your bridge tilt data [2], but not >>>> enough to make it useful. I still think this problem presents a >>>> relevant challenge for HTM, and I think with more time and effort, >>>> someone might be able to create a real solution. I, unfortunately, >>>> have other projects I have to work on. :( >>>> >>>> > So outside of >>>> > Hotgym, what really compelling demos do you have? I've been away >>>> > for a while so maybe I missed something... >>>> >>>> My current favorites are location-based anomaly demos like these: >>>> - https://github.com/nupic-community/mine-hack >>>> - https://github.com/numenta/nupic.geospatial >>>> >>>> I am also working on a new tutorial, coming within a couple weeks >>>> (hopefully). >>>> >>>> > I am also rather concerned HTM needs swarming before it can model >>>> > anything. Isn't that "cheating" in a way? It seems the HTM is >>>> > rather fragile and needs a lot of help. The human brain does not >>>> > have this luxury it just has to cope with whatever data it gets. >>>> >>>> Swarming is hard to explain. In the brain, input data to the >>>> neocortex comes from sensory organs, which have been tuned by >>>> millions of years of evolution to have very specific >>>> characteristics that process incoming light, sound, movement, etc. >>>> into certain patterns of nerve excitations. These patterns get >>>> generated outside the cortex, but they are still important to >>>> attempt to replicate in some ways. All data in "reality" must be >>>> represented to the cortex somehow outside of that reality. In >>>> NuPIC, this is what encoders so. They translate data coming into >>>> them into a representation similar to a vector of nerve excitations. >>>> >>>> Anyway, swarming is a very rough way to simulate evolution in the >>>> sensory organs. It randomly sets up encoders with different >>>> parameters (also spatial pooling and temporal memory parameters) >>>> and tries to find the best possible set of configurations for the >>>> specific data that is being processed. Your cochlea have had >>>> millions of years to come to that perfect set of configuration >>>> parameters ;). Swarming is a brute-force attempt to resolve some >>>> set of parameters for a specific input data set. It is not always >>>> right, it takes a long time, and it sometimes requires manual >>>> intervention, but it definitely very useful for finding groups of >>>> configurations that work well for certain types of data. >>>> >>>> > I'm also not convinced the neocortex is everything as Jeff >>>> > Hawkins thinks. I seriously doubt the bulk of the brain is just >>>> > scaffolding. >>>> > I've been told birds have no neocortex but are capable of very >>>> > intelligent behaviour including constructing tools. Meanwhile I >>>> > don't see any AI robot capable of even ant-like intelligence. >>>> > (ants are >>>> > amazing!) Has anyone even constructed a robot based on HTM? >>>> >>>> While I know nothing about bird brains, except that they have a >>>> cerebral cortex that has some similarities to the mammalian cortex, >>>> I do know that hierarchy in the neocortex is a generally accepted >>>> theory in neuroscience. >>>> >>>> We could still learn a helluva lot from the lower levels of the >>>> brain (imagine a flight vehicle that could control itself as >>>> efficiently as a fly), that just isn't what we're trying to do at Numenta. >>>> >>>> > Personally I don't think a a disembodied computer can ever be >>>> > intelligent (not even ant-like intelligence). IMO a robot (and it >>>> > must BE a robot) needs to be embodied with sensory-motor loop at >>>> > the core of its functionality to start behaving like an animal. >>>> >>>> You don't need to have physical interaction with the world to have >>>> behavior. There are millions of actions that can be taken on the >>>> internet that all have consequences, change the landscape for the >>>> actor, and present different possible actions in return. The most >>>> obvious example is video games, but the internet in general is a >>>> very large universe with no physical structure, but endless virtual >>>> structures to interact with. >>>> >>>> [1] >>>> https://github.com/numenta/nupic.research/wiki/Current-Research-Tas >>>> ks [2] https://github.com/nupic-community/bridge-tilt >>>> >>>> Regards, >>>> >>> >>> >>> >>> -- >>> With kind regards, >>> >>> David Ray >>> Java Solutions Architect >>> >>> Cortical.io >>> Sponsor of: HTM.java >>> >>> [email protected] >>> http://cortical.io >> >> >>
