Category unsupervised-learning

An Introduction to Virtual Adversarial Training

Virtual Adversarial Training is an effective regularization technique which has given good results in supervised learning, semi-supervised learning, and unsupervised clustering.

An Overview of Deep Learning Based Clustering Techniques

This post gives an overview of various deep learning based clustering techniques. I will be explaining the latest advances in unsupervised clustering which achieve the state-of-the-art performance by leveraging deep...

Category semi-supervised-learning

An Introduction to Virtual Adversarial Training

Virtual Adversarial Training is an effective regularization technique which has given good results in supervised learning, semi-supervised learning, and unsupervised clustering.

Category image-segmentation

A Beginner's guide to Deep Learning based Semantic Segmentation using Keras

Pixel-wise image segmentation is a well-studied problem in computer vision. The task of semantic image segmentation is to classify each pixel in the image. In this post, we will discuss...