Re:Good, freely-available textbooks in machine learning
by T_S_ on Tuesday September 28, 2010 @07:24PM
(#1737753)
Not sure neural net expert Yann LeCun (yann.lecun.com) would agree with your neural networks comment. Neural nets have taken on a life of their own since the time they were originated and actually have little direct connection with neuroscience these days.
[ Parent
| on HN ]
Re:Good, freely-available textbooks in machine learning
by alextp on Tuesday September 28, 2010 @08:35PM
(#1737884)
This is true, but the very good deep learning results are very recent (from less than 5 years ago), and they generally require very different models and/or training strategies from the standard multilayer perceptron you find in most AI textbooks. So it's an omission, but I'm not aware of any textbooks that cover these new neural networks in depth, as basic research in this area is still going in a frantic pace.
Re:Good, freely-available textbooks in machine learning
by Groxx on Tuesday September 28, 2010 @09:02PM
(#1737940)
Yeah, I'm finding that there's little book-format info on deep neural networks as well. Similarly for belief networks. Gotta hunt down some journals, and wield some Google-fu.
Re:Good, freely-available textbooks in machine learning
by tudorachim on Tuesday September 28, 2010 @09:48PM
(#1738035)
The most promising approaches for neural nets these days involve learning generative models using Restricted Boltzmann Machines (RBMs). Geoffrey Hinton at UToronto has some good seminal papers on these, like http://www.cs.toronto.edu/~hinton/absps/ncfast.pdf. See http://www.cs.toronto.edu/~hinton/ for excellent videos of digit generation / classification.
As a note, this approach outperforms all others (sans tweaks), whereas neural nets used to be beaten by SVMs and the like.
Re:Good, freely-available textbooks in machine learning
by alextp on Tuesday September 28, 2010 @09:53PM
(#1738047)
Actually, the best recent results in this area involve discriminatively trained stacked auto-encoders using second-order algorithms (for which the code, as of Sept 2010, is still private to the group at the university of toronto), as described in James Martens's paper at this year's ICML: http://www.cs.toronto.edu/~jmartens/docs/Deep_HessianFree.pd...