Led a 4 person team and implement a Neural Sign Language Translation (NSLT) model,
which can generate spoken language translations from sign language videos.

Worked in a team of 35 people and created a machine learning model that identifies regional clusters in Nigeria where renewable energy microgrids are both most viable and likely to have a high impact on the community.

Build a Generative Adversarial Neural Network to super resolve an image by an up- scaling factor of x4.

Implemented a model DEX which predicts apparent age and gender from a single image without facial landmarks.

Extracted character-based TF-IDF features from training data and then trained them on a MLP. Given an unknown paragraph, it predicts the dominant language (among 235 different languages).

Implemented Neural Style Transfer, it is an algorithm that given a content image C and a style image S, can generate an artistic image. The overall style cost function is obtained using several hidden layers and optimizing the total cost function results in synthesizing new images.

Worked on YOLO, which is a state-of-the-art object detection model that is fast and accurate. It runs an input image through a CNN which outputs a 19x19x5x85 dimensional volume.