Even though separated by thousands of kilometre, the small island nation of Ireland shares old ties with India. Ireland provided the foot soldiers that administered the British empire in India. From the other side, Annie Besant, a British national of Irish descent, was instrumental in establishing Banaras Hindu University, a prominent centre of education that helped families across Norther India get access to modern education.

%t-test used heavily in statistics originated in the Guiness brewery by William Gosset Photo by Tavis Beck on Unsplash

But lost in mists of time, there is probably even another possible uncanny connection. Irish legends allude to a Goddess Danu (a mother Goddess) who came to Ireland from sea. …

We live in the age and time of remakes and remixes of movies, and music. Hollywood has always been good at it. Particularly Disney has made remakes of its popular stories like The Parent Trap (1961 and 1998) and Lion King (1994 and then 2019). Bollywood has legalised shameless plagiarism as creative inspiration, with many of its popular movies and songs being uncredited scene by scene remakes of movies.

Theatrical Release Poster for Disney’s The Lion King (2019)

What was an unexpected surprise that the God’s themselves sometime engage in creative remix. Bhagwad Gita is a discourse given by Lord Sri Krishna in a battlefield to Pandava Prince Arjuna…

In this article let us look at the architecture of a Question Answering system, and we can build one using a pre-trained Question Answer model based on BERT. But before that let us do a quick recap of what we have learned in this series so far. …

In the previous part of this series we had a look at transformers. Transformers have become the work horse of Natural Language Processing tasks. Transformers are based on attention that allows them to use the entire input text while maintaining focus on the important parts of the input text. Transformers use a feed-forward neural network that scales with parallel processing infrastructure when compared to the Recurrent Neural Networks (RNN) used earlier for text processing.

BERT is a popular character in American TV show Sesame Street [Source: pixabay.com]

A word embedding is a vector representation of a word. Machine Learning algorithms use word embeddings. In this article we will look at BERT (Bidirectional Encoder…

In the previous article in this series (Part 3) we talked about the different data sets that can be used to build and benchmark Question Answer models. Each of these data sets maintain leader boards recording the top performing models on the data set. You will find transformers, and transformer based architectures if you dive into the top models on the leader board of these datasets.

In this article we will present a high level overview of attention, and transformers which form the building block of most modern Question Answering models.

Attention is all about identifying the rights pieces of the input that should be used for the task at hand. Photo by Elena Taranenko on Unsplash

Recurrent Neural Network (RNN)

RNN is a type of neural network which can…

In the previous post of this series (Part 2) we looked at a taxonomy for build Question Answering systems. We looked at information retrieval based Question Answering systems developed using supervised machine learning based Question Answer models. We need data to develop Question Answer models. Thankfully, there are data sources available in the open space that can be used to develop and benchmark Question Answer models. In this post we will look at four such data sets.

Data is the new oil. Data is required to train supervised Question Answer models. This articles is about four open data sets that can be used train Question Answer model. Photo by Zbynek Burival on Unsplash

Let us do a quick recap of Question Answer models, before we look at the data sets. Question Answer models are supervised machine…

In the first part of this series we looked at how Question Answering systems can help organizations unlock the information available in their data stores to improve productivity and end user experience. In this part let us look at the different ways to build Question Answering systems. The Question Answering systems are based on the following two paradigms: knowledge based, and information retrieval based [1]. Knowledge based questions answering systems typically use the knowledge from the document corpora captured in a knowledge graph to answer a query. …

Deep though commissioned by a race of hyper-intelligent pan-dimensional beings could communicate in natural language and had the capability to answer complex questions — In “The Hitchhiher’s Guide to the Galaxy” by Adam Douglas,

Question Answering is a promising application of Natural Language Processing (NLP). For organizations it offers the promise to unlock the information hiding inside the document stores and make it available to the stakeholders in a timely and swift manner. The aim of this series is to introduce the readers to question answering systems and demonstrate the use of existing libraries to quickly build a question answer system using pre-trained BERT embeddings. In the first part of this series let us look at the relevance of Question Answering systems for a modern organization. …

Photo by LinkedIn Sales Navigator on Unsplash

Natural Language Processing (NLP) is one of the most sought-after machine learning skills with applications across a variety of business domains. The state of art and application in NLP has benefitted immensely from the exponential progress within the space of deep learning. If you are interviewing for a NLP position then expect lots of questions from the deep learning space. In this post, I am enumerating some popular questions specifically focussed on NLP that may help with your interview preparations. Happy practicing!!

  1. What is a word embedding?
  2. What all word embedding you are aware of?
  3. Describe the approach used by…

Sunny Deol essaying the role of Maj. Kuldeep Singh Chandpuri in Border(1997) a Bollywood flick which presents a dramatized but thoroughly entertaining portrayal of the decisive Indian victory in the Battle of Longewala. Indian forces decimated an enemy equipped with far superior equipments thanks to outstanding military acumen and planning.

The real success of machine learning models is when they move from the safe havens of Proof of Concept (POC) and Minimum Viable Prototype (MVP) to the big bad world of the production environment. The most well-intentioned and technically superior models may fail to deliver the desired business outcome in the production environment due to poor planning and infrastructure. This article distills my experience with deploying machine learning models to identify the key pieces of functionality that are required for a successful machine learning model deployment. Please do mention is comments if I have missed something.

Create A Production Parallel Environment

Creating a production parallel…

Atul Singh, PhD

Data scientist, with extensive experience of design, development, and industrialization of AI/ML based solutions for financial services and telecom.

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