Slashdot Log In
Jeff Hawkins' Cortex Sim Platform Available
Posted by
kdawson
on Tue Mar 06, 2007 10:26 PM
from the build-a-brain-at-home dept.
from the build-a-brain-at-home dept.
UnreasonableMan writes "Jeff Hawkins is best known for founding Palm Computing and Handspring, but for the last eighteen months he's been working on his third company, Numenta. In his 2005 book, On Intelligence, Hawkins laid out a theoretical framework describing how the neocortex processes sensory inputs and provides outputs back to the body. Numenta's goal is to build a software model of the human brain capable of face recognition, object identification, driving, and other tasks currently best undertaken by humans. For an overview see Hawkins' 2005 presentation at UC Berkeley. It includes a demonstration of an early version of the software that can recognize handwritten letters and distinguish between stick figure dogs and cats. White papers are available at Numenta's website. Numenta wisely decided to build a community of developers rather than trying to make everything proprietary. Yesterday they released the first version of their free development platform and the source code for their algorithms to anyone who wants to download it."
Related Stories
[+]
Science: Building Brainlike Computers 251 comments
newtronic clues us to an article in IEEE Spectrum by Jeff Hawkins (founder of Palm Computing), titled Why can't a computer be more like a brain? Hawkins brings us up to date with his latest endeavor, Numenta. He covers progress since his book On Intelligence and gives details on Hierarchical Temporal Memory (HTM), which is a platform for simulating neocortical activity. Programming HTMs is different — you essentially feed them sensory data. Numenta has created a framework and tools, free in a "research release," that allow anyone to build and program HTMs.
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Future Plans (Score:2, Funny)
Right... (Score:5, Insightful)
Re: (Score:2, Informative)
Plus, he's sure because he's proposing a solution to the 'unsolved problem.'
Re: Not one year, seven or eight years (Score:4, Informative)
Actually, its content was produced seven or eight years ago.
Its publishing date was "December 2005". But publishers will lie about the publication date of a book if it allows them to sell more books. And in this case, I wouldn't be surprised if the book came out hot off the presses in December 2004 with a postdate of "December 2005"
Furthermore, this book was based on the scientific proceedings of a conference which occurred six years before the book was finally edited (or finally published). I'm actually not sure of the year of the scientific conference itself, because the information supplied to sell the book doesn't give the actual year.
Parent
Re:Right... (Score:5, Interesting)
Parent
Life's work (Score:3, Funny)
Some people spend their entire adult lives trying to overcome alcohol addiction, or trying not to beat their spouse. To others, it comes naturally.
Re:Right... (Score:4, Insightful)
That is a wonderful thing, though. First of all, claims can be tested. They'll either live up to the description, or they won't. If the don't, another path not to go down in a particular manner has been identified, and that is useful. OTOH, if they are verified, then we may have a key to a form of cognition. Whether it is our kind or not is really not as important as just the fact that it is some kind.
Aside from that, I found some very interesting things in his descriptions of the HTM. For instance, I found the following precise description of enabling religious behavior: First, he describes how HTMs handle specific, non-overlapping domains (and of course this doesn't mean that another HTM can't relate those to each other.) One might handle financial markets, another speech, another cars. Then he says "After initial training, an HTM can continue to learn or not" Emphasis mine. So you can set up an HTM in a learning situation where you limit the input to descriptions consisting of sensory data of any arbitrarily limited set of patterns you like, get it to see the world represented by those patterns as you wish, and then disable learning for that particular HTM. Other HTMs can continue to learn, but that one is "frozen." Sounds like the perfect recipe for a priest or supplicant to me. Does that not sound like the very core definition of "unshakable faith"?
For all the doubt being thrown this fellow's way, you know, eventually someone will come up with something like this and it will be a working model of such a system. It's a tough problem, very abstract and requiring a lot of insight, but as with all problems discovered to date where we can actually get our hands on the system under study, there is no indication that any part of it exists in any way outside the sphere of nature and the natural rules we already know - and we know a lot of basic rules.
Kudos to him for sinking his teeth into the problem, and for coming up with results that can be tested, and for letting them loose into the word for such testing. If he's wrong, he's helping. If he's right - he's going to be mentioned in the same breath with a lot of very important people for a very, very long time to come.
Parent
Re: (Score:3, Interesting)
Most "grand-scale theories of brain operation", in fact, fail to make claims that can be tested, at least not in the foreseeable future. They predict the large-scale algorithms by which the brain operates. They do not make any claims as to the behavior of any individual neurons, and this is the dat
Re: (Score:3, Informative)
Yes; his reasoning is laid out in the beginning of this document. [numenta.com] The thinking seems quite reasonable to me, as far as it goes. AI is my area of research.
Why (Score:2)
Its been my experience that the most brilliant people have a fiduciary target at some point, and its oft quoted here that the best are those whole love it and do it for the pleasure, rewards aside. Recent studies re funding of the kernel would bear out my point. Personally i feel a core of dedicated staff with external input will yield the best results (ala firefox) but this is not open per se.
This will cause problems (Score:2, Insightful)
Re: (Score:3, Interesting)
it has to be said (Score:2, Redundant)
High-Quality Video Link (Score:5, Informative)
Enter the Matrix (Score:3, Funny)
drawing recognition (Score:2)
Yeah, but can it distinguish the invention of PalmOS Graffiti from the invention of PARC Unistroke? That would have been handy...
Software you can really get into... (Score:2)
Then, of course, there's always the dream of eventually being able to really 'get into the code' and debug it from the inside, leading to the soviet joke where "the code debugs you."
Ryan Fenton
System Requirements (Score:3, Insightful)
Confidentiality agreement a killer (Score:5, Informative)
almost... (Score:3, Interesting)
http://en.wikipedia.org/wiki/Baum-Welch_algorithm [wikipedia.org] http://en.wikipedia.org/wiki/Viterbi_algorithm [wikipedia.org]
The first is an alogorithm which utilizes forward and back-tracking "to find the unknown parameters of a hidden Markov model." The second is a similar algorithm used for learning 'known' causes (for reference).
I work in computational linguistics and the time an algorithm takes to run and the amount of memory it requires are serious limitations. That's why ad-hoc systems are so common.
Cortex Sim == Bullsh*t (Score:5, Interesting)
Here is what many people in machine learning and computer vision think about Hawkins stuff:
- it's way, way behind what other people in vision and machine learning are doing. Several teams have biologically-inspired vision systems that can ACTUALLY LEARN TO RECOGNIZE 3D OBJECTS. Hawkins merely has a small hack that can recognize stick figures on 8x8 pixel binary images. Neural net people were doing much more impressive stuff 15 years ago.
- Hawkins's ideas on how the brain learns are not new at all. Many scientists in machine learning, computer vision, and computational neuroscience have had general ideas similar to the ones described in Hawkins's book for a very long time. But scientists never talk about philosophical ideas without actual scientific evidence to support them. So instead of writing popular book with half-baked conceptual ideas, they actually build theories and algorithms, they build models, and they apply them to real data to see how they work. Then they write a scientific paper about the results, but they rarely talk about the philosophy behind the results.
It's not unusual for someone to come up with an idea they think is brand new and will revolutionize the world. Then they try to turn those conceptual ideas into real science and practical technologies, and quickly realize that it's very hard (the things they thought of as mere details often turn out to be huge conceptual obstacles). Then, they realize that many people had the same ideas before, but encountered the same problems when trying to reduce them to practice (which is why you didn't hear about their/your ideas before). These people eventually scaled back their ambitions and started working on ideas that were considerably less revolutionary, but considerably more likely to result in research grants, scientific publications, VC funding, or revenues.
Most people go through that "naive" phase (thinking they will revolutionize science) while they are grad students. A few of them become successful scientists. A tiny number of them actually manage to revolutionize science or create new trends. Hawkins quit grad school and never had a chance to go through that phase. Now that he is rich and famous, the only way he will understand the limits of his idea is by wasting lots of money (since he obviously doesn't care about such things as "peer review"). In fact, many reputable AI scientists have made wild claims about the future success of their latest new idea (Newell/Simon with the "general theorem prover", Rosenblatt with the "Perceptron", Papert who thought in the 50's that vision would be solved over the summer, Minsky with is "Society of Minds", etc......).
No scientist will tell Hawkins all this, because it would serve no purpose (other than pissing him off). And there is a tiny (but non-zero) probability that his stuff will actually advance the field.
- Anonymous Scientist
Re:Barrier to entry (Score:5, Insightful)
Not so much dare to be stupid, but rather the Socratic, don't be afraid of exposing your own ignorance - don't lose your opportunity to learn by merely being embarrassed of people thinking you dumb while you take your first few steps in a new landscape.
But do take notes and research the small topics you are uncertain of after your first adventure into to the topic. Perhaps you'll need to learn a bit about XML/XSL, perhaps you'll need to find out the anatomy of a nerve cell to understand some explanations. If nothing else though - get into it because it is a fun adventure and a lot of cool stuff to learn.
Ryan Fenton
Parent
Re:Barrier to entry (Score:4, Informative)
He's also done some lectures available on Google Video [google.com].
Parent
Re: (Score:3, Interesting)
If you are interested in the field of AI with neural like computing, your best bet is to learn a huge amount of math. Really you can't understand anything without knowing at least 2nd year linear algebra. That's if you just want to basically understand what's going on. If
Re: (Score:3, Insightful)
As a current student in neuroscience, you should know better than to make such a sweeping and inaccurate presumption. There are many paths to working models and working theories, and very few of them include "integrating all levels of research" or anything remotely similar. It is entirely possible to code up (for example) a brand new, highly functional sorting method without either knowin