Shruti Jadon
Looking for Full-time Opportunities in the field of Machine Learning Research
Experimental Study on Capsule Networks
This project focuses on Latest form of neural networks which claims to beat the convolutional neural networks in terms of efficiency and accuracy. For this project, we have experimented with different datasets, which consists of specific features(such as images with a lot of information, images with sparse information etc.), and tried to come up with optimal hyper-parameters values for different domain of datasets. ReadMore...
Schema Matching using Machine Learning
Schema Matching is a method of finding attributes that are either similar to each other linguistically or represent the same information. In this project, we take a hybrid approach at solving this problem by making use of both the provided data and the schema name to perform one to one schema matching and introduce creation of a global dictionary to achieve one to many schema matching. We experiment with two methods of one to one matching and compare both based on their F-scores, precision and recall. We also compare our method with the ones previously suggested and highlight differences between them. Read More...
Video Summarization
Video is one of the robust sources of information and the consumption of online and offline videos has reached an unprecedented level in the last few years. A fundamental challenge of extracting information from videos is a viewer has to go through the complete video to understand the context, as opposed to an image where the viewer can extract information from a single frame. In this project, we attempt to employ different Algorithmic(Motion Analysis, HOG Threshold Method) and Deep Learning methodologies(LSTMs) to find an effective way of summarizing a video by extracting the important key frames from it. Read More...
One Shot Learning with Siamese Networks
The lack of a large amount of training data has always been the constraining factor in solving a lot of problems in machine learning, making One Shot Learning one of the most intriguing ideas in machine learning. This project focuses on improving the accuracy of Image Classification, when very less amount of data is given, using Siamese Neural Networks and Bayesian Inference. ReadMore...
Air Pollution Analysis
Recent Climate Change Paris agreement has shaken the world, as it was showing how much earth climate has changed, and slowly reaching its danger zone. This project focuses on analysis of pollution levels at various locations inside USA. It involved extracting dynamic data from airnow site (directing from NASA data) and visualizing it using various graphs, which helps in analyzing the key factors which are responsible for pollution at a specific area. We also used different Machine Learning prediction algorithms to predict the pollution level in nearby future of a given area.
