Siddharth Agrawal

Learn More
Entity Resolution is the task of identifying which records in a database refer to the same entity. A standard machine learning pipeline for the entity resolution problem consists of three major components: blocking, pairwise linkage, and clustering. The blocking step groups records by shared properties to determine which pairs of records should be examined(More)
Finding connected components in a graph is a well-known problem in a wide variety of application areas such as social network analysis, data mining, image processing, and etc. In this paper, we present an efficient and scalable approach in MapReduce to find all the connected components in a given graph. We compare our approach with the state-of-the-art on a(More)
For big data practitioners, data integration/entity resolution/record linkage is one of the key challenges we face from day to day. Entity resolution/record linkage with high precision and recall on a large graph with billions of nodes, and hundreds of times more edges poses significant scalability challenges. Similarity based graph partition is still the(More)
AIM The aim of this study was to establish a correlation between macular thickness on optical coherence tomography (OCT) and 2 visual functions (visual acuity and contrast sensitivity [CS]) in established cases of primary open angle glaucoma (POAG). MATERIALS AND METHODS A total of 50 consecutive patients of established POAG between 40 years and 70 years(More)
PURPOSE To evaluate a simplified method for correction of ocular deviation in patients of infantile and acquired basic esotropia. MATERIALS AND METHODS Thirty-six consecutive patients of infantile and acquired basic esotropia were selected for this study. Patients underwent unilateral recession-resection surgery as per the new norm gram. Patients(More)
There has been much debate, sci-fi movie scenes, and several scientific studies exploring the concept of robot authority. Some of the key research questions include: when should humans follow/question robot instructions; how can a robot increase its ability to convince humans to follow their instructions or to change their behaviour. In this paper, we(More)
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate , leading to tremendous progress. However, there have been limited efforts(More)