Pritish Jadhav, Mrunal Jadhav

Neural Machine Translation - French to English

Sun, 12 Jul 2020 by Pritish Jadhav, Mrunal Jadhav / Deep Learning, NLP

A sequence to sequence model lies behind numerous systems which we use on a daily basis. In this blog, we will try to give a short and concise explanation of the sequence to sequence model and apply it to achieve significant results on pretty complex tasks of machine translation.

Read more

Hierarchical Attention Network For Multilabel Classification (Detailed Case study)

Wed, 11 Sep 2019 by Pritish Jadhav, Mrunal Jadhav / Deep Learning

In many real-world data applications, often we encounter scenarios where each data point may belong to multiple classes. A multilabel classifier is trained to predict the K most likely classes among N possible classes. The article focuses on solving multi-label text classification problems using the Hierarchical Attention Network.

Read more

Proving Convexity of Mean Squared Error Loss in a Regression Setting.

Sun, 25 Aug 2019 by Pritish Jadhav, Mrunal Jadhav / Linear Algebra

The article covers step-by-step proof for proving the convexity of a mean squared error loss function. The Ability to test convexity for different loss functions can come in handy especially with more and more exotic loss functions being proposed every day.

Read more

The Curious Case of Convex Functions

Sat, 24 Aug 2019 by Pritish Jadhav, Mrunal Jadhav / Linear Algebra

The convexity property of a function unlocks a crucial advantage where the local minima of a convex function is also a global minima. This ensures that a model can be trained where the loss function is minimized to its globally minimum value. In this blog post, we shall work through the concepts needed to prove the convexity of a function.

Read more

Training Classifier Using PyTorch - Detailed Example.

Wed, 26 Jun 2019 by Pritish Jadhav, Mrunal Jadhav / Deep Learning

As a part of "Getting Acquainted with Deep Learning Frameworks" series, in the article we shall explore Pytorch Library. Pytorch is a deep learning library developed by Facebook Researchers. The focus of this article will be to highlight the steps involved in training a multiclass classifier using Pytorch.

Read more

Deep Neural Network for Multiclass Classification Using Keras.

Wed, 19 Jun 2019 by Pritish Jadhav, Mrunal Jadhav / Deep Learning

Getting started with deep learning frameworks often involves a steep learning curve. This article is aimed at providing a gentle introduction to building DNN models with Keras which can be scaled and customized as per dataset. The focus will be on understanding the syntax and good practices involved in building a complex DNN model rather than achieving accuracy.

Read more

TextRank Algorithm for Key Phrase Extraction / Text Summarization.

Fri, 24 May 2019 by Pritish Jadhav, Mrunal Jadhav / Data Science

Extracting Key Phrases from Textual data is a problem faced across domains. In this Article, we shall explore an approach which leverages Google's pagerank algorithm to solve the problem. Basic knowledge of Linear Algebra, Markov Chains and Text Parsing would help in comprehending the content.

Read more

Auto Dream11 Selector

Mon, 03 Dec 2018 by Pritish Jadhav, Mrunal Jadhav / Data Science

With all the buzz around Indian Premier League (IPL), FIFA World Cup, Cricket World Cup-2019, fantasy sports websites like Dream11 are gaining traction. Fanatsy Sports Portal allows sports fans like me to be a part of it. Having said that, it is very difficult to keep track of all the players and their performance across the sports. In this Tutorial, I will try to automate the fantasy selection process so that the probability of winning a fantasy league is maximized.

Read more

Product Classificatication Using Image and Text (Deep Learning)

Wed, 10 Oct 2018 by Pritish Jadhav, Mrunal Jadhav / Deep Learning

Image classification using deep learning and its applications has been proving its worth across business verticals.However, building an image centric AI product is often marred by Unavailability of large amounts of data, poor quality of images, etc. Often the metadata / textual data associated with these images are ignored. In this article, we shall try and build a DL model that can leverage image as well as textual data.

Read more

Binary Classification using Logistic Regression using numpy

Sun, 08 Jul 2018 by Pritish Jadhav, Mrunal Jadhav / Machine Learning

Logistic Regression is one the most basic algorithm on ML. With the likes of sklearn providing an off the shelf implementation of Linear Regression, it is very difficult to gain an insight on what really happens under the hood. This tutorial is aimed at implementing Logistic Regression from scratch in python using Numpy.

Read more

Linear regression using numpy

Fri, 08 Jun 2018 by Pritish Jadhav, Mrunal Jadhav / Machine Learning

Linear Regression is one the most basic algorithm on ML. With the likes of sklearn providing an off the shelf implementation of Linear Regression, it is very difficult to gain an insight on what really happens under the hood. This tutorial is aimed at implementing Linear Regression from scratch in python using Numpy.

Read more