IBM creates a research group to test Numenta, a brain-like AI software(technologyreview.com)
technologyreview.com
IBM creates a research group to test Numenta, a brain-like AI software
http://www.technologyreview.com/news/536326/ibm-tests-mobile-computing-pioneers-controversial-brain-algorithms/
9 comments
Interesting timing for me, I just stumbled across Clortex[0] which is an implementation of Hawkins' HTM in Clojure today after watching How To Make a Brain in Python[1] which may be interesting to anyone that likes this stuff.
[0] http://fergalbyrne.github.io/
[1] http://motherboard.vice.com/read/how-to-make-a-human-brain-i...
[0] http://fergalbyrne.github.io/
[1] http://motherboard.vice.com/read/how-to-make-a-human-brain-i...
'On intelligence' is the book that got me started on my journey in pursuit of AGI. I look forward to seeing the results from this. Video summary :
http://youtu.be/izO2_mCvFaw
Numenta's based upon the hierarchical temporal memory model described in the book On Intelligence. It's an attempt to replicate the structure of the neocortex.
Mathematically it appears to be just another neural network. IMHO, deep learning is probably more likely to give systems approximating general intelligence.
Mathematically it appears to be just another neural network. IMHO, deep learning is probably more likely to give systems approximating general intelligence.
That's not really correct actually. A better way to look at it is that each neuron in the HTM is itself effectively a deep neural network. The HTM is a temporally aware hierarchy of these neurons.
Can deep learning algorithms learn from temporal data ? So far I have seen object recognition from a single image but not some intelligence gathering from a video.
Yes, they are called recurrent neural networks. The disadvantage is higher memory and time requirements. You need to store the state of the neural network at every time step, and then at the end iterate through the whole process in reverse.
Whereas best I understand it, HTM is online and updates the weights every time step without needing to keep a running memory of the states it's been in.
Whereas best I understand it, HTM is online and updates the weights every time step without needing to keep a running memory of the states it's been in.
> Mathematically it appears to be just another neural network.
What's the difference, broadly speaking?
> IMHO, deep learning is probably more likely to give systems approximating general intelligence.
If HTMs are just another neural net, why do you suspect deep learning will excel comparatively?
I don't know the first thing about HTMs - just curious.
What's the difference, broadly speaking?
> IMHO, deep learning is probably more likely to give systems approximating general intelligence.
If HTMs are just another neural net, why do you suspect deep learning will excel comparatively?
I don't know the first thing about HTMs - just curious.
HTMs are biologically accurate -- they do the same thing as the neurons in our neocortex! The most exciting aspect of Numenta's research is that they are building algorithms which think the way we do (albeit in early stages right now).
Re: "HTMs are biologically accurate": It depends on what you mean by accurate.
Hawkins argues that HTMs capture the systems-level effect of a brain, even if software models of neurons are not the same as biological neurons.
I can't personally comment on what others say about the accuracy, even at the systems-level.
Re: "The most exciting aspect of Numenta's research is that they are building algorithms which think the way we do (albeit in early stages right now)." It is a stretch to use the word "think" in this way, since thinking suggests consciousness. One wouldn't say we "think" when we simply observe. You might argue that HTMs pass signals in an analogous way -- that might be a fair statement, from Hawkins' point of view.
Yes, I realize that Hawkins says some interesting things about 'forward' and 'backward' processing even for 'low-level' processing such as edge detection.
Hawkins argues that HTMs capture the systems-level effect of a brain, even if software models of neurons are not the same as biological neurons.
I can't personally comment on what others say about the accuracy, even at the systems-level.
Re: "The most exciting aspect of Numenta's research is that they are building algorithms which think the way we do (albeit in early stages right now)." It is a stretch to use the word "think" in this way, since thinking suggests consciousness. One wouldn't say we "think" when we simply observe. You might argue that HTMs pass signals in an analogous way -- that might be a fair statement, from Hawkins' point of view.
Yes, I realize that Hawkins says some interesting things about 'forward' and 'backward' processing even for 'low-level' processing such as edge detection.
> described in the book On Intelligence
Said book spends a good deal of time on criticizing neural networks, FYI.
Said book spends a good deal of time on criticizing neural networks, FYI.
Of course I read it. Fascinating concept, but I'm unimpressed by Numenta's execution. Certainly the ideas of a single neocortical algorithm, a temporal feedback loop minimizing error, the relationship between the hippocampus and the rest of the memory-learn-predict-observe-correct cycle are inspired.
It will be very interesting to see their findings. As far as I know Numenta's software (or HTMs in general) haven't been tested yet against known benchmarks like LSVRC, CIFAR, etc. Or results haven't been published.
I thought I had heard of Numenta. I looked it up and was reminded that it is a project of Jeff Hawkins, the inventor of the PalmPilot.
original article at http://www.digitaltrends.com/computing/ibm-creates-a-researc...
Actually that appears to be yet another wrapper around this: http://www.technologyreview.com/news/536326/ibm-tests-mobile...
Thanks. Url changed to that from http://www.futurism.co/links/view/ibm-creates-a-research-gro....
Even after many years of talk about HTM, I've yet to come across one result which shows HTM outperforming other ML algorithms on any of the myriad data sets out there. Isn't it time they showed something? Anything?
Biologically inspired engineering is a great thing, but to say something is a model of the neocortex in a meaningful way is a claim no one deserves to make in 2015.
I see a lot of patents for HTM, but have there been any peer reviewed publications from Numenta?
Jeff Hawkins himself states "HTM does not present any new idea or theory, but combines existing ideas to mimic the neocortex with a simple design that provides a large range of capabilities". Ok got it. Nothing wrong with competing on implementation and engineering.
So regarding that implementation, how are they doing against competitors in their space?