Document Level Question and Answering This blog gives overview of Question and Answering problem, various categories of Question and answers, and existing datasets on question and answering. Introduction Document Level Question and Answering is an active area of
Importance of Exploratory Data Analysis Exploratory Data Analysis is an important aspect of Data Science. It helps in understanding the distribution of the dataset and more. One way of approaching EDA is to create questions and build visual
Visualizing COVID19 case occurrence in AR The way we present data to others has evolved from simple pie charts/bar graphs to sophisticated interactive visualizations. These interactive visualizations are built using techs like Augmented Reality or Virtual Reality. There
COVID-19 COVID-19 .. a log A log of the evolution, found info and analysis by the labs team about COVID-19, focused on India.
The evolution of Identity Management Models and an introduction to Self Sovereign Identity(SSI) We all know internet was a very niche place back in late 1960's. A small elite clubs from government, engineers or people who worked for NASA, CERN etc had access to the internet.
Blockchain Diagnosing PostgreSQL database performance issue We have been working on Stellar blockchain for quite some time. Recently, we got an opportunity to work on a POC (Proof of concept) to build payment infrastructure on blockchain. It was an
A quick introduction of Biometrics In this blog, our purpose is to take an in-depth look at how biometrics works. Among multiple types of biometrics like Facial characteristics, Fingerprints, Iris pattern etc. which are fairly complex to understand,
Group Equivariant Convolutional Networks The current Deep Learning tend to be data intensive because they need to be taught all the types of invariances one would expect during inference. But humans are very efficient at recognising already
statistics Expected Value of Lottery Ticket How can you calculate the expected value of a lottery ticket and how it help us to tell buying lottery ticket can give better ROI or not !
statistics Is it Possible to Predict Lottery Number Is the Lottery data has any patterns ? Can we use this data for any analytical or ML related tasks. In this post we discuss the different aspects of the lottery system and randomness of lottery system.
What do Bert embeddings capture The word embeddings by Bert [1], a transformers [2] based architecture for NLP tasks are known to capture the context in which the word is used. We explore how does the embedding space
Rudimentary Sequence Alignment using Coronavirus Genome Pairwise sequence alignment is a useful tool in many fields of biology. For example, the similarity between sequences can used be in evolutionary analysis to find out what organisms share a common ancestor.
data labeling Snorkeling in Data for Supervision and Generation Let's Start with 'Why?'Most of the preprocessing phase of pipelines has the complexity of taking the unstructured data or the Dark Data like text, Tables, Image, etc, and turning into the structured
Alternate Realities A Survey on Presence in Virtual Reality The current growth in usage of virtual environments has given to some unique experiences and is mostly applied in specialist domains such as psychometry education and entertainment. Even though the direct benefit from
Virtual Reality Data Visualization in VR Introduction In recent times, a tremendous amount of data is being generated every day. We use mobile phones, IoT devices, GPS, social media and so on, which are the sources of this huge
CRF with spatial features for Named Entity Recognition IntroductionThe extraction of relevant information from unstructured documents is one of the most important tasks in Natural Language Processing (NLP). Named Entity Recognition (NER) is a specific task of NLP which aims at
Computer Vision RGB v/s HSV for Computer Vision Computer vision is an interdisciplinary scientific field that deals with how computers can be made to gain high-level understanding from digital images or videos. If we consider Digital images then it can be
Useful Image Preprocessing techniques in OCR pipeline Image Binarization with Convolutional Neural Networks We have been using Tesseract for extracting text from document images. Our in-house dataset consists of images of documents captured using mobile phones, scanners and digital PDFs.
Talk: The nuts and bolts of WebAssembly I gave a talk at the “Mixed Nuts @ Pramati” meetup on 2019-08-24 10am-12pm on WebAssembly. This post contains notes from the talk - sort of almost-transcript.
Machine Learning ∂P and DP - things that change the ML game Differentiable programming and Data programming are two approaches that may just change the accessibility of ML to solve many problems.
Deep Learning Shabda - A Neural Speech Denoiser IntroductionIn speech processing, an important task encountered most often is the removal of noise from the given audio signal. Most of the time it happens that we are in situations where we want
Named tensor dimensions are a good idea One can only suffer tensor index manipulation for so long. A team at Hardvard NLP group has proposed what they call Named Tensors, which use string names instead of tensor dimension indices. An
Uncertainty estimation and its applications in Active Learning The concept of uncertainty is introduced in Machine learning models to give us a measure of how confident the model is about its predictions. A brief survey of the recent advances in this
GAN A brief survey on GANs Generative Adversarial Network (GAN) is one of the most interesting and popular class of generative networks in deep learning. GANs are finding applications in a variety of fields ranging from automated vehicles to
Understanding how confident is a Deep learning algorithm about its predictions? Deep learning is finding applications in a wide variety of fields and is also known to perform better than humans in some of the tasks such as image classification. Although the predictions of
