Hacker News Reader

Comment by mayank | Hacker News Reader

> There's very little about neural networks, for instance, or genetic algorithms

For good reason. Outside of neuroscience, there's very little reason to use neural networks for classification or regression problems, and outside very ill-posed optimization problems, there's very little reason to use genetic algorithms. If you want a good MODERN machine learning book (which is where your post seems to imply your interests lie), try the Elements of Statistical Machine Learning by Tibshirani, Hastie and (I forgot the third guy's name, sorry). Anyway, it's included in the posted link.

View on HN

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.

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.

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.

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.

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...

Reply on news.ycombinator.com