Sign in

Live. Learn. Laugh. CS Undergrad at NIT Trichy
Photo by Alina Grubnyak on Unsplash

Knowledge graphs have taken many by storm. Its ability to represent data and derive inferences have proved to be a game changer for information representation and retrieval. In this article, we shall go through ontologies, discuss a few examples. We then dive into knowledge graphs and discuss an interesting application as well.

An ontology models generalized data, that is, we take into consideration general objects that have common properties and not specified individuals. A ‘building’ would be a generalized model while the ‘Taj Mahal’ is a specific entity. Using these models, we create a conceptualisation which is a simplified and…

Source: ETH Zurich

‘I can identify if a person is suffering from pneumonia via X-rays’, I told my brother. He looked at me in shock, knowing that I was a CS student and had never touched biology after middle school. However, I had achieved that feat and had results to prove it. 😝 Anyways, it seems cool, right? Well, it’s all possible thanks to deep learning! In this article, we will understand and make a convolutional neural network to identify pneumonia given X-rays.

In a previous article, I have talked about creating neural networks; in case you aren’t very clear regarding the basics…

Source: Create


What if I said instead of opening the internet to find your favourite team's latest score, you could receive them via WhatsApp? Sounds cool right? Well, it’s not too challenging. All it requires is a basic understanding of web automation and the structure of websites.

Before we get started with the actual code, let us familiarize ourselves with a couple of concepts.

The purpose of web scraping is to extract data from a website. This alternative is used when there is no API available to retrieve information.

Web scraping, web harvesting, or web data extraction is data scraping used for…

Ever had a bunch of features while training a model but couldn’t figure out which ones are best suited? You might have come across principal component analysis, PCA for short, at that juncture.

You may lose out on a bit of accuracy and information, but it sure does simplify the process for you.

Photo by National Cancer Institute on Unsplash

In a very crude sense, PCA is a dimensionality reduction technique. If you’re working on a project that has an enormous dataset with multiple features, you might want to reduce some of them. …

Photo by Alina Grubnyak on Unsplash

Is that a cat? Is it a dog? Well, let us create a neural network and find out! Neural networks have become an integral part of image classification, natural language processing, speech recognition and whatnot. This seemingly complex entity isn’t that complex, after all. Let us get down to the basics and build our very own neural network!

The primary objective of neural networks is to replicate the human brain and take decisions and perform tasks just like we all do. Our nervous system consists of billions of neurons, and each neuron receives impulses from input sources like our eyes…

Photo by Tim Gouw on Unsplash

Beep! Beep! Beep! It’s 6 in the morning as my alarm goes off. I stare at the wall and snooze for another 15 minutes. As my eyelids shut, I remember the possibility of a surprise quiz that may happen! I jump out of bed and turn on my laptop, hyperventilating as I think about it. My sister shouts at me for switching on the lights so early in the morning. What a start to the day I think to myself, but then, this has been going on for quite some time right?

As I touch upon the topics covered in…

Photo by Stanislav Kondratiev on Unsplash

We use summarizations in many places in our lives. While reading about a book, the blurb at the back provides us with a general idea about it. News apps often have small captions that talk about the article and movie reviews are another place where summaries prove to be extremely valuable.

With the advent of technology such as natural language processing (NLP) and machine learning, why not use them to generate summaries without human intervention?

Before you decide to summarize your textbook for the upcoming exam, let us learn some important concepts.

Summarization of a text can be of two…


This multiplication algorithm is particularly important for dealing with large numbers and reducing the computation time by using the concept of divide and conquer!

Traditional multiplication has the running time O(n²) while the Karatsuba algorithm is O(n^(1.59)).


Why do we need Network Security?

Network security is the practice of preventing and protecting against unauthorized access to a network. This security measure takes into consideration the manner in which devices (nodes) in a network interact with one another. Network security goes hand in hand with endpoint security, wherein individual devices are the prime focus. It ensures that the network is free from unauthorized access to modify, misuse, destroy and/or malfunction the infrastructure and data. As a result, a suitable network security provides a safe environment and a secure infrastructure for users, devices, programs and data to run.

The 3 Phases of Network Security

  1. Protection: configuring all the devices in the…

Source: Valley News


I’d like you all to visit this site before proceeding with the article. As the URL suggests, these people don’t exist in reality. All the faces are fake (in other words, computer-generated). So, how are such realistic faces created by a machine that has zero IQ? Credit goes to GANs, a concept founded by Ian Goodfellow in 2014.

These faces are created by a generative adversarial network (GAN for short). A GAN comprises of two neural networks…Wait wait wait! What’s a neural network?

In simple terms, it’s an algorithm that detects patterns and draws correlations between various features. A dataset…

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