Large Scale Distributed Deep Networks (by Jeff Dean et al)

It's like a game of "Where's Waldo" on freaking crack.

You have literally no idea how complex this stuff is now then do you?

One of the trends these days is to perform automatic hyper-parameter tuning, especially for cases where a full exploration of hyper-parameters via grid-search would mean a combinatorial explosion of possibilities (and for neural networks you can conceivably explore dozen of hyper-parameters). A friend of mine just got a paper published at NIPS (same conference) on using Bayesian optimization/Gaussian processes for optimizing the hyper-parameters of a model -- http://www.dmi.usherb.ca/~larocheh/publications/gpopt_nips.p.... They get better than state of the art results on a couple of benchmarks, which is neat.

The code is public -- http://www.cs.toronto.edu/~jasper/software.html -- and in python, so you could potentially try it out (runs on EC2, too).

Btw, Geoff Hinton is teaching an introductory neural nets class on Coursera these days, you should check it out, he's a great teacher. Also, you can always come back to Google, we're doing cool stuff with this :)

Topics will be presented in multiple ways (simple and intermediate) so you can have plenty of different views on the same material. The material works as both zero-knowledge intro to the topics as well as quick refreshers if you haven't seen the material in a while (quick -- what's an eigenvector?!).

The launch courses will be 1.) real-world applications of probability and statistics (signal extractions), 2.) linear algebra for computer science, and 3.) wildcard (a random assortment of whatever the heck we think is important or entertaining to know). Future courses are: introduction to neural networks, introduction to computational neuroscience, introduction to deep learning, advanced deep learning, how to take over the world with a few dozen GPUs, avenues by which google will become irrelevant, and robotics for fun and evil.

This is phase zero of a four phase plan. I'll get some pre-launch material together to shove down HN shortly, then it'll launch a few days later. Hopefully you'll hear about the project again.

In theory stochastic gradient descent allows you to escape local minima: the noise in the stochastic error surface will likely be enough for the network to escape whatever minimum it is in. Practically, because weights will tend to have a large magnitude and because most of the times you'll be using a saturating non-linearity (such as a sigmoid), the number of steps required to escape that local minimum might be too big.

Presumably, you could use second-order optimization methods to perhaps escape from minima -- because it allows you to make "bigger" steps -- but that comes with its own set of problems (negative curvature being one of them).

I encourage you to actually test these hypotheses: train a simple network on something stupid like MNIST, and make it achieve a reasonable error with many passes through the data. Then change the labels of 10-20-50% of your inputs and continue training (with the same learning rate... or not!) to see how long it takes for the network to get to another minimum.