Worked on extracting named entities like organizations, countries, persons, and events from New York Times Article and a few other Articles. Named entity recognition (NER) is probably the first step towards information extraction that seeks to locate and classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities of times, quantities, monetary values, percentages, etc

Worked on a dataset of Images from a Car front CAM. This labeled dataset is used to train the model which predicts the Steering Angle of the car. The same model can be used to predict the braking, and acceleration of cars using some additional data from GPS, LiDAR, and other kinds of sensors.

I took a GAN model for Semi-Supervised learning and trained it on the Street View House Number dataset. I Used the GAN discriminator to make a prediction of house numbers. I used TensorFlow to serve my model in a Docker container. I have created a client to request the scores for the number of images. Then, I deployed the model into a cloud.

Worked on Brain-MRI Dataset to build a model that can detect Tumorous parts of the brain using MRI scans. For Patients with a brain tumor, the first step in treatment is often surgery to remove as much of the mass as possible. A tumor sample is obtained and analyzed during surgery, which can help to precisely diagnose the tumor and define the Margins between the tumor and healthy brain tissue. However, such intraoperative pathology analysis takes time. The sample must be processed, stained, and analyzed by a pathologist while the surgeon and patient wait for the results. This process can be simplified using vast data of medical records available.