My first deep learning project- Dog Breed Identification

In this playground Kaggle competition, you are provided with strictly canine subset of ImageNet in order to practice fine-grained image categorization. How well you can tell your Norfolk Terriers from your Norwich Terriers? With 120 breeds of dogs and a limited number training images per class, you might find the problem more, err, ruff than you anticipated. Link to github

January 1, 1970

Dengue Predicting Disease Spread

Demonstration on an Application for Disease Analytics predictive analytics framework by an application for disease analytics. Specifically, we apply the framework to predict dengue cases in San Juan, Puerto Rico. Link to github

January 1, 1970

Detection of Pneumonia from Chest X-Ray

Training a classifier on medical images is a crucial task to aid doctors and provide lower cost services to patients. If we can build a classifier that can diagnosis a given disease and provide it to patients who can’t afford a doctor as an app, we have a scalable business. In this project, I have demostrated to perform transfer learning to predict pneumonia in a patient, given their chest x-ray data using Custom Deep Convololutional Neural Network and by retraining pretrained model “InceptionV3” with 5856 images of X-ray