BIRCH is a very cleaver clustering algorithm which is very fast in practise. At the end of its clustering, it guaranties that the average cluster radius is bounded. This is...

This article is about a technique to make any series of computations differentiable. We will demonstrate the technique to derive back propagation algorithm in a slightly weird way. A generalised...

Introduction We have a dataset which represents each sample and the class it belongs to by . The objective of classification problem is to develop a model, which when given...

In the post about Linear Discriminant Analysis, we have seen how to implement a classifier using generative assumption. Let's built a linear classifier with discriminative assumption. Softmax Classifier Imagine we...

How will it look like if each digits of \(\pi \) is colored? Code is in the source of this web page.

In this post, I'll show you how to easily build a linear classifier. LDA classifier In the previous post, I have show derivation of Linear Discriminant analysis for binary classification....

In the post on bayes error, we discussed what is the best classifier if the features are not enough to tell the class. We also derived that in such situation,...

What is the best classifier you can build when your data is not enough to predict the labels? The God Function In an ideal world, everything has reason. Every question...

A new poster Coauthored with Abhay Kumar and Anuroop Iyengar has been accepted at Nvidia GPU Technology Conference. The poster title: Domain Adaption of Image Caption Model for Video Descriptions....