In this article, I’ll initially be discussing about generating adversarial images and then I’ll slowly steer the discussion towards an interesting paper published by researchers at Google Brain about an Adversarial Image Patch ( This paper presents a generic image patch, which when added to images would cause any Neural Network to misclassify them. The authors of the paper themselves have demonstrated this through a youtube video :

Let’s first find out why such adversaries can be formed in the first place.

Weaknesses of Neural Networks

Deep Neural Networks have certainly been producing “high accuracy” results for object recognition lately. Yet, one can…

Deep Learning has been an exponentially growing field in the past decade or so. And to show my enthusiasm for the field, I’m starting this series in which I’ll pick up a published paper related to deep learning (or at least something close enough) every one or two weeks, and do some sort of an analysis on the paper and give more insights into it. This way I felt I could make the community aware of some of the recent advances in Deep Learning and also arouse the curiosity of fellow Deep Learning enthusiasts.

Before I get started on today’s…

In today’s world, GAN (Generative Adversarial Networks) is an insanely active topic of research and it has already attracted a lot of creative applications like this one

At least for about a decade now, there have been drastic improvements in the techniques used for solving problems in the domain of computer vision, some of the notable problems being, Image classification, object detection, image segmentation, image generation, image captioning and so on. In this blog post, I’ll briefly explain some of these problems and also I’ll try to compare and contrast these techniques from how humans interpret images. I’ll also steer the article towards AGI (Artificial General Intelligence) and pitch in some of my thoughts on that.


Before we dive deeper, let’s get some motivation from how some…

As a Google Intern at Hyderabad, I got introduced to a couple of really cool libraries (TensorFlow and FlumeJava) that use the so called Deferred Execution Model. I found some very interesting similarities between the two libraries and in this blog post, I’ll seek to discuss on how deferred execution works by taking instances from the two libraries. I’ll also discuss the pros and cons of Deferred Execution.

What is Deferred Execution ?

The term Defer simply means to postpone. This is exactly what happens in Deferred Execution too. Every variable or operation is just deferred on a dependency graph. The dependency graph is a…

Shravan Murali

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store