Index ¦ Archives ¦ RSS

Denoising Images and Markov Random Fields

Denoising Images and Markov Random Fields

Undirected Graphical models have remained elusive to me for a long time. One of the best ways to strip away the abstractness around them is to see how it works in the real world. One of the easiest and first real world examples of such models, also called the Markov Random Fields, is in denoising an image.

What's wrong with histograms and what are density estimators?

Estimating Probablity Densities

The other day I was reading Parzen's density estimators in Bishop. Density estimators are a non-parametric way of estimating the underlying probability distributions, that might have generated the data that you are handed over. Parametric methods consist of assuming a distribution, and then estimating the parameters ...

Are Iowa polls predictive?

What do Iowa polls tell us?

Everyone is staring hard at the polls in Iowa and trying to predict who the winners will be. There are data gurus, there are journalists, and everyone in between. But are these Iowa polls that predictive? I decided to look at the polls 4 ...

Tale of Two Bandits: Bayesian and Greedy

The Bayesian Bandit and the Greedy Bandit

First post, test.

Pelican is cool.

© Sourav Chatterjee. Built using Pelican. Theme by Giulio Fidente on github.