Jeff Hawkins' Cortex Sim Platform Available

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."

Comments

Right...

[Bugpowda]

I'm still a bit confused as to how he is so confident that this is how the neocortex works given that this is still one of the 23 unsolved problems in system neuroscience. But hey, he made a lot of money off Palm, that gives him way more street cred than people who have been working on this problem for their whole lives.

Re:Right...

[fyngyrz]

his claims were quite, uhm, let's say, "ambitious".

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.

Re:Right...

[ougouferay]

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.

Surely we have plenty of humans available to do tasks 'curently best undertaken by humans' :)

Seriously though... while it might be useful to develop AI systems in this area as timesaving devices, the examples given above aren't really in that category - IMO AI research could be better applied to tasks humans can't achieve so easily (and maybe provide an insight into why that is the case) - I guess I just don't buy into the whole 'we can make something just like a human - but that isn't one' view of AI.

Re:Right...

[Anonymous Coward]

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: [standard description of training a classification algorithm on data] Sounds like the perfect recipe for a priest or supplicant to me. Does that not sound like the very core definition of "unshakable faith"?

No, it sounds more like you should share whatever it is you've been smoking...

What you've described applies equally well to, say, Fisher's Linear Discriminant. You optimize the algorithm on a set of data points, and then you can apply it to some other data if you like. If you think that's an adequate model for human reasoning and consciousness, then maybe you are the one with the strange beliefs...

This will cause problems

[TubeSteak]

I read that and thought "a new, more advanced algorithm for breaking CAPTCHAs"

Re:Barrier to entry

[RyanFenton]

Don't be so afraid of complexity - Slashdotters make fun of themselves for diving into things uneducated (not reading the articles, not RTFM), but really, the only way to cope with such an informationaly complex landscape such as computing is to sometimes just be willing to go unprepared and be willing to make mistakes, and to ask stupid questions.

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

System Requirements

[cmacb]

How unusual to see software that will run on OS X or Linux, but there is no Windows version. Shape of things to come I hope.

Before anyone else says it

[rhythmx]

Someone needs to immediately train this to catch /. dupes and/or run Linux.

Re:Hmm....

[fyngyrz]

In order to understand exactly what the cortex is doing you must integrate all levels of research into your studies.

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 knowing all the other methods, the theory underneath them, or even the theory underneath your own. It is possible to move your arm without knowing a thing about partial differential equations, yet you can't really model it easily without them using traditional approaches. So get down off that high horse. I think the thin air has addled your thinking.