Student Blogs


Mercari Price Suggestion Challenge- A Machine Learning Regression Case Study

The modern age is the age of machine intelligence. These are such buzzwords that has taken the world by storm and almost every avenue has enjoyed the flavor of Machine Learning in some way. Today, I am going to take you through a real-world data science problem which I have picked from Kag ...

Quora insincere question classification

An existential problem for any major website today is how to handle toxic and divisive content. Quora is a platform to gain & share knowledge where you can ask any question and get answers from different people with unique insights. At the same time, it’s important to handle the toxic co ...

Attention Mechanisms

  Sequence-to-sequence learning (Seq2Seq) is all about models that take a sequence as an input and outputs a sequence too. There are many examples and applications of this but today I will focus on one specific application which is a machine language translation. For eg English to Hindi. Th ...

TalkingData AdTracking Fraud Detection

Fraud risk is everywhere, but for companies that advertise online, click fraud can happen at an overwhelming volume, resulting in misleading click data and wasted money. Ad channels can drive up costs by simply clicking on the ad at a large scale. With over 1 billion smart mobile devices in active ...

Pseudo-Labeling to deal with small datasets — What, Why & How?

To climb the AI ladder with supervised learning may require “teaching” the computer all the concepts that matter to us by showing tons of examples where these concepts occur. This is not how humans learn: yes, thanks to language we get some examples illustrating new named concepts ...

Text Classification with Extremely Small Datasets

As the saying goes, in this era of deep learning “data is the new oil”. However, unless you work for a Google, a Facebook or some other tech giant, getting access to adequate data can be a tough task. This is especially true for small companies operating in niche domains or personal pr ...

Time Series Analysis and Forecasting

Real applications of forecasting are almost never done in isolation. They are typically one part — a crucial part — of an overall quantitative solution to a business problem. This is certainly the case at Harrah’s Cherokee Casino & Hotel in North Carolina, as explained in a ...

Malaria Detection

In this case study, we will learn how to detect Malaria using cell images and CNN architectures. With the advancement in Deep Learning architectures, this is fairly easy. Our objective for this case study would be to develop a system which can detect this deadly disease without having to rely en ...

End to End deployment of ML App

In this blog, we will learn how to create a simple web and android application and deploy our deep learning models in cloud  Click here to check his complete article.   ...

Deep learning model that can recognize the voice of a artist

Speaker recognition is the identification of a person from characteristics of his/her voice is an important human trait most take for granted in natural human-to-human interaction/communication. It is also called voice recognition. There is a difference between speaker recognition&nbs ...

Self driving AI terrorizing the great city in NFS RIVALS

[embed]https://vimeo.com/279828315[/embed]   [embed]https://vimeo.com/279828315[/embed]   The overall goal of this project is to explore general artificial intelligence. When considering environments to employ AI models into, games are an obvious choice. I have personally chosen ...

Can machines predict and prevent crimes?

Contrary to popular Hollywoodish imaginations, machines are yet to emerge as super-humans that can outsmart, or even match human intelligence. But there are some areas in which machine intelligence can support, or at times outwit, the limited neurological ability of the human brain. Predictive p ...

Exploratory Data Analysis of Kaggle Machine Learning & Data Science Survey 2018

This exploratory data analysis is based on the survey data conducted by Kaggle on machine learning and data science in 2018. It is Kaggle’s second annual Machine Learning and Data Science Survey. The data set which has been published on Kaggle contains 23859 responses from 147 countrie ...

Introduction to Linear Algebra

Linear Algebra is the study of vectors, vector spaces and mapping between vectors. In this blog, we'll study about vectors, the transformation of vectors and basis vectors.   Click here to read more. ...

With GAN’s World’s first AI generated painting to recent advancement of NVIDIA

This is a review article on the history of GAN's and the math behind it. Click here to read more. ...

Art of becoming The Sherlock Holmes: A comprehensive guide to Pandas

This tutorial teaches you the necessary skills to deliver valuable insights from data using Python’s data analysis library, Pandas. The datasets used in this tutorial is available and taken from Kaggle. Get a complete hands-on guide on Pandas methods and attributes listed below and learn ...

A Complete Guide To Boosting Ensembles

Boosting is one of the ensembling technique which becoming more and more popular day by day. No doubt boosting works phenomenal but people often assume it as a black box model and therefore this blog will give a tour to boosting ensembles covering its introduction, mathematics behind it, classif ...

A Gentle Introduction to Decision Tree Learning

Decision tree learning is a method for approximating discrete-valued target functions, which is a part of supervised learning, where we learn a mapping from input to output by analyzing examples for which true values are given by a supervisor or a teacher or a human being which is generally trea ...

A complete guide to predicting the severity of an accident

This blog post explores how severe an accident can be. Its specially meant for beginners who feel difficult what to do in a data science project. considering this being “my first project” I have attempted to make it precise and as simple as possible. First and foremost task is specif ...

Data Visualization using Python for Machine Learning and Data science

As we all knew that there is a huge buzz going over the term data, like Big data, Data science, Data Analysts, Data Warehouse, Data mining etc. which emphasize that, In the current era data plays a major role in influencing day to day activities of the mankind. Every day we are generating more t ...

Getting started with Natural Language Processing: Easy, Quick & In-Depth (Part I)

I have gone through many blogs on Natural Language Processing, but couldn’t find any blog which could explain to me how a specific algorithm works or the mathematical theory behind the NLP strategies. My aim is to explain NLP in a very easy manner without sacrificing the quality of content ...

Deep Neural Network for Classification from scratch using Python

In this article, I will tell about What is multi-layered neural network and how to build a multi-layered neural network from scratch using python. In this article, I am focusing mainly on multi-class classification neural network. Below are the three main steps to developing a neural network. ...

In the end, Machine-Learning is all about Optimization: ft. Gradient Descent

We all know Machine-Learning is all about solving complex optimization problems, it can be a simple linear-regression with few weights or a Deep Neural-Network with millions of weights to train. Here training the weights essentially means minimizing the Loss-function(through which we measure our ...

Application of Hypothesis Testing and Spearman’s rank correlation coefficient to demystify Suicides worldwide

To show the use of statistical methods in real-world problems, for finding out if there is some statistical significance of an assumption we make after primary analysis of a data set. Here we will explain and apply two well known statistical techniques: 1. Hypothesis Testing 2. Spearman&rsq ...

AWS with Android

Amazon Web Services (AWS) provides on-demand cloud computing platforms to individuals an companies and in addition to that, it also provides various Machine Learning APIs. Anyone can leverage the power of these APIs to create a state of the art Machine Learning project.       ...

A Primer into Neural Networks

This is an introduction to Neural Networks where I attempt to distill high-level Artificial Intelligence concepts into plain English and everyday analogies. This guide is intended for those who have no understanding of the sub-field of Deep Learning and would like to get a broad overview. ...

The Ultimate NanoBook to understand Deep Learning based Image Classifier

There are many tasks like image classification, object localization, object detection, object segmentation and many more. But in this post, we will primarily focus on image classification. This post is divided into three sections. In the first one, We will try to build this technique by follo ...

Fulfillment lies in creating something

This Blog post aims to provide a complete intuitive understanding of Generative Adversarial networks along with mathematics that goes with it, including the Tensorflow implementation of it. Click here to read more. ...

Creating Rest API with Pre-trained Machine Learning Models and Deploying it in Cloud

Modern applications running in the cloud often rely on REST based Micro Services architecture. In this article,I will build Restful Micro services(Rest API) with pre-trained ML model using Django Rest Framework and deploy it in Google App engine of Google Cloud Platform. This article requires joi ...

Image Captioning with Keras — “Teaching Computers to describe pictures”

Well, some of you might say “A white dog in a grassy area”, some may say “White dog with brown spots” and yet some others might say “A dog on grass and some pink flowers”. Definitely, all of these captions are relevant for this image and there may be some o ...

Building “Pokédex” in Android using TensorFlow Lite and Firebase’s ML Kit

This post is a continuation of a series of earlier blogs on Mobile Machine Learning using Firebase’s ML Kit. In this series, I’ve explored a number of resources that could be used to build smart apps. While the default APIs provided in ML Kit is powerful in covering the basic use ca ...

Data Visualization using Matplotlib

Data Visualization is an important part of business activities as organizations nowadays collect a huge amount of data. Sensors all over the world are collecting climate data, user data through clicks, car data for prediction of steering wheels etc. All of these data collected hold key insights ...

There’s LIGHT even in the DARKEST places..Deep learning helps you show the light..

    Have you ever thought that low light photography can be as good as daylight photography? Seems impossible right?, but Deep learning makes it possible. Using deep learning pipeline, you can take an image in dark with low exposure time and convert it to an image which is ...

There’s LIGHT even in the DARKEST places..Deep learning helps you show the light..

      Have you ever thought that low light photography can be as good as daylight photography? Seems impossible right?, but Deep learning makes it possible. Using deep learning pipeline, you can take an image in dark with low exposure time and convert it to an image whi ...

There’s LIGHT even in the DARKEST places..Deep learning helps you show the light..

      Have you ever thought that low light photography can be as good as daylight photography? Seems impossible right?, but Deep learning makes it possible. Using deep learning pipeline, you can take an image in dark with low exposure time and convert it to an image whi ...

Judging a book by its cover..! -Karthik Nooney

      Contrary to the popular adage “Don’t judge a book by its cover”, a book cover can actually be used to get a potpourri of information about the book. The cover of a book is often the first interaction and it creates an impression on the reader. It starts a co ...

Deep dive into multi-label classification..! --Karthik Nooney

With continuous increase in available data, there is a pressing need to organize it and modern classification problems often involve the prediction of multiple labels simultaneously associated with a single instance.   Known as Multi-Label Classification, it is one such task which is omnipr ...

Deep dive into multi-label classification..! --Karthik Nooney

With continuous increase in available data, there is a pressing need to organize it and modern classification problems often involve the prediction of multiple labels simultaneously associated with a single instance.   Known as Multi-Label Classification, it is one such task which is omni ...

Facial Expressions Recognition--Hina Sharma

Now-a-days there is a common trend for a human-computers interaction in the field of machine intelligence. Real time detection of face and interpreting different facial expressions like happy, anger, sad, fear, surprise etc. is based on facial features and their actions. The key elements of face are ...

A guide to an efficient way to build neural network architectures- Part I --Shashank Ramesh

“If you listen to your intuition you will always know what is the best for you”   That is what is said when people give lessons on life, well it might be true for life but for training neural networks this is what i believe   “Trust your intuition but also your lo ...

A guide to an efficient way to build neural network architectures- Part II

This article is a continuation to the article linked below which deals with the need for hyper-parameter optimization and how to do hyper-parameter selection and optimization using Hyperas for Dense Neural Networks (Multi-Layer Perceptrons)   A guide to an efficient way to build neural netw ...

Personalized Cancer Diagnosis --Tulasi Ram

Exploratory Data Analysis and all machine learning models What is business problem we needed to solve?   Let us discuss briefly about data and business problem.Because it is very important to understand the business problem we are solving.   When a patient seems to have a canc ...

Celebrity Face Generation using GANs

Generative adversarial networks (GANs) are one of the hottest topics in deep learning. (GANs) are a class of artificial algorithms used in unsupervised learning algorithm, implemented by a system of two neural networks 1. Generator 2. Discriminator Both networks are contesting with each o ...

Exploration Of Wines --Hina Sharma

In this blog as the name suggests “Exploration Of Wines”, she is explains how to identify the different varieties of wines based on their descriptions by doing sentiment analysis and using some Machine Learning text related predictive models. click here to check my complete ar ...

Handling Missing values -Rahul Vasumani

How does the real world data exist ?   Most of the data is being extracted from various sources namely from traditional databases, real time data (sensor data), manual survey data, sound data, sequential data (gene data) and so on..   What all can go wrong when working with data? ...

Intrepetability of KNN -Tulasiram

Cancer is an abnormal disease.As in olden days it is very hard to detect cancer.But when the ML is used in medical domain it is found easy to detect some of the dangerous diseases like pneumonia,cancer etc…The ambit of ML is extended to detect cancer.From the past 20 years Machine Learning ...

How e-commerce websites show similar products which you search? - Krishna Dheeraj

Let us begin with a most familiar scenario in online shopping. We are searching for Macbook Air on Amazon.com. When we scroll down the product page in the end we get to see similar products like Macbook, Macbook Pro and other Apple related accessories and items. How did Amazon.com suggest you to l ...

KHOJ- Simplifying Product Research

When we plan to purchase and product(like a smartphone) , we conduct extensive research of the product category for features, prices, customer-reviews, video-reviews on Youtube and ask our friends know the product category very well. This phase of product purchasing is called product-research. Curre ...

Vis Vibro --Diagnosing machine failures

Vibration Analysis is one of the most critical and widely used methods in predictive condition monitoring of mechanical devices. Most of this analysis is performed using industry grade accelerometers as transducers along with custom-built hardware and software to process the accelerometer data to pr ...

DeepTrader - Stock Trading Using DeepLearning

Quantitative trading uses statistical and probabilistic methods to predict the future stock price of equities and commodities. This is a fairly well developed and researched area. We are leveraging recent advances in NLP for processing news articles, Sequence modeling using Deep Learning and Deep Re ...