Month: January 2015

Kernels Part 1: What is an RBF Kernel? Really?

An intriguing article. To look at an RBF kernel as a low pass filter is something novel. It also basically shows why RBF kernels work brilliantly on high dimensional images. Given that your image features generally lie in a continuous domain, an RBF kernel generally can fit smooth solutions and thereby create more relevant separating hyperplanes,especially in case of multiple classes.


My first blog on machine learning is to discuss a pet peeve I have about working in the industry, namely why not to apply an RBF kernel to text classification tasks.

I wrote this as a follow up to a Quora Answer on the subject:

I will eventually re-write this entry once I get better at Latex.  For now, refer to 

Smola, Scholkopf, and Muller, The connection between regularization operators and support vector kernels

I expand on one point–why not to use Radial Basis Function (RBF) Kernels for Text Classification.  I encountered this  while a consultant a few years ago eBay, where not one but 3 of the teams (local, German, and Indian) were all doing this, with no success  They are were treating a multi-class text classification problem using an SVM with an RBF Kernel.  What is worse, they were claiming the RBF calculations…

View original post 686 more words

An Interesting History of Computer Vision

Dr. Fei Fei Li from Stanford discusses the advent and growth of computer vision in recent years. Particularly intersting is her recent research on multimodal interactions and large scale visual recognition. This has been primarily made possible due to the growth in GPU technology. I hope to try out Theano and Caffe for deep learning in this scenario soon.


Recent Publications from L. Fei Fei’s group: