Work Ex

Research Intern, MILA Quebec-AI Institute

Designing generative flow networks so as to jointly generate DNA sequences as well as the fidelity (precision level of the approximate estimation of energy of the sequence) of the oracle to evaluate the sequence.
I am working under Alex Hernandez-Garcia, in Yoshua Bengio's group.

Designed a C++ infrastructure to provide clients with transparency on the corporate actions that have impacted their securities.
Integrated the service with database accessor and reporting framework APIs.
Designed the UI and monitoring dashboard on Humio for the service. Deployed the service on Beta platforms.

Worked with the Tufts Neutrino Group, under Dr. Taritree Wongjirad on the MicroBoone experiment.
Designed a generative network to simulate neutrino events conditioned on the particle’s momentum.
I'm also a junior investigator at IAIFI.

Implemented Single Image Super Resolution Convolution Neural Networks to downsample Sea Surface Temperature (SST) fields of Bay of Bengal from a spatial resolution of 15 km to 5km and 5km to 1km.

Built a pipeline capable of detecting six classes of wrinkles on human faces irrespective of their age, gender or face tone.
Experimented with image processing techniques like Binarization, Gaussian Filter and Hessian Line Tracking in order to highlight them.
Certain wrinkles (like those around the eyes) are more common than others. I selected the RetinaNet architecture to tackle the imbalanced dataset.
The pipeline achieved a Mean Average Precision (maP) of 0.5. It was deployed on the CureSkin application, with over a million downloads.

Developed a service for JioLiv, and devised an intelligent algorithm based on structural similarity index to filter out non-redundant movie frames.
Implemented a Tensorflow-based text detection and recognition pipeline to read words off the movie frames.
Subsequently, I formulated a logic using spaCy and TextRank to extract contextually significant phrases (single-worded or multi-worded) from the generated text.

Built a pipeline to detect price tags from images of supermarket shelves and interpret prices from them.
To detect minuscule price tags, the Single Shot Object Detector based on Feature Pyramid Network was implemented.
A YOLO-based Multi-Digit Classifier was trained to read digits off the price tags.
The entire pipeline achieved a Mean Average Precision (mAP) of 0.6, and is being deployed by Xplorazzi Technologies. [View Details]