The Subgradient
   Archive    Feed    About

Because life is continuous and differentiable almost everywhere

Learning Errors

I finally had the chance to give the ImageNet winners a read-through. It’s Microsofts Deep Residual Learning technique that allowed them to learn a convnet of 150 layers. Sure, Google matched them in classification error but their localization error blew everyone else out of the water. The idea behind their technique was that each layer learns the residuals instead of an entire mapping function. That is, each layer of the network adds on to the previous layer instead of finding a complete mapping function. It’s kind of intuitively obvious that this is a better way to learn deep networks than trying to do the entire thing in one shot now that you think about it.

Read more

NIPS 2015: Through the Looking Glass

NIPS being the first conference I’ve been to was somewhat of a information overload. That said, it was probably one of the most educational weeks I’ve had, catching up on the state of the art in deep learning, admiring how pretty Bayesian techniques are and simultaneously how they’re never used for one reason or another. Montreal probably had the best weather ever for this time of the year – it was so warm that I passed with a light jacket and flip flops during the middle of the conference. But enough said, let’s talk about NIPS 2015.

Some warning: My expertise is mostly in deep learning. Some of the impressions I got of other subjects may be wildly incorrect.


Overall the tutorials were well advertised, just an introduction to topics at hand. Jeff Dean and Oriol Vinyals talked about Tensorflow. Tensorflow pretty much follows in the footsteps of Theano, creating computational graphs that you can compile and run on the GPU. The upside is that it has millions of dollars thrown at it, so it’s almost definitely going to be better supported. Though a couple people tested Tensorflow and found it slow at first, it’s definitely getting faster and better. At the same time, Jeff announced the state-of-the-art on ImageNet with a different inception architecture, dubbed ReCeption, halving the error from last year. It was a big deal until ImageNet announced results a couple days later and Microsoft beat them in both classification and localization error.

Sorry Google! Sorry Google!

Read more