jmares

Re:What Hinton’s Google Move Says About the Future of Machine Learning on Thursday March 21, 2013 @12:57AM (#5413019)

Data shows, as you say, that small scale performance is no indicator of large scale performance.

How then do you decide which projects are worth trying on the large scale?

Re:What Hinton’s Google Move Says About the Future of Machine Learning on Wednesday March 20, 2013 @07:53PM (#5411592)

Dear Googlers, it would be interesting to know how computational resources are allocated to new ideas (eg. Kurzweil's PRTM-based NLU system) at each stage, from prototype genesis to mature technology. What are the factors that come into play?

How are metaphors processed in Kurzweil's PRTM?

Posted by jmares on Wednesday January 16, 2013 @03:19PM
from the self-post dept.

For those of you interested in Ray Kurzweil's new Pattern Recognition Theory of the Mind, and metaphors in AI:<p>In "How to Create a Mind", Ray says:<p>“The third and most powerful method is the ability to combine two lists. One list can have a set of transformations that we have learned may apply to a certain category of pattern; the cortex will apply this same list of possible...

( Read More... | no comments | on HN )

Re:Innovation and the Bell Labs Miracle on Thursday March 01, 2012 @11:37AM (#3652791)

Thanks jpdoctor. Could you elaborate on what you mean by formal defn? Who defined them, out of which principles or goals? (I understand that this might have multiple answers)

Re:Innovation and the Bell Labs Miracle on Monday February 27, 2012 @01:52AM (#3638036)

Could you tell us about project genesis at Bell Labs? How did projects originate, grow, and get killed or morphed?

Thank you.

Re:Stanford Free Classes – A review from a Stanford Student on Wednesday December 28, 2011 @02:18PM (#3400960)

I took CS229 at Stanford.

ml-class.org does a phenomenal job in equipping you with the practical knowledge needed to apply the tools of machine learning to real problems.

There is no reason why learning to use these tools should be hard. If you want a challenge, there are plenty of problems in the world amenable to solution via machine learning, especially in today's data deluge.

If you want a deep mathematical appreciation of the algorithms and their derivation, you should do CS229, not CS229a.