Ok, so what does this mean to those of us who don't do deep neuroscience-based machine learning that often?
Basically, what problem (problems?) does this algorithm actually solve?
Basically, what problem (problems?) does this algorithm actually solve?
No references in their paper.
The smells like Wolfram's "New Kind of Science" type work. And they are welcome to prove me wrong, I like AI topics. But it is isolated from other peer work, when AI field is not new. So kind of suspicious.
However, Hawkins work is similar to Deep Neural Nets in that both are unsupervised neural nets (unlike perceptrons and back-prop) and both aim to represent data as sparse representations. Also, here's a similar question I answered on Quora: http://www.quora.com/Machine-Learning/Does-Numenta-build-on-...
In addition, Numenta does use CLA's to solve real problems for customers: https://www.groksolutions.com/solutions.html
Finally, Hawkins' book, On Intelligence, has at least inspired researchers like Stanford's Andrew Ng at a philosophical level which he talks about IIRC in his online ML course. https://class.coursera.org/ml/class
"Systematic experiments on three line-drawing datasets have been carried out to better understand HTM peculiarities and to extensively compare it against other well-know pattern recognition approaches. Our results prove the effectiveness of the new algorithms introduced and that HTM, even if still in its infancy, compares favorably with other existing technologies."