The projects in this portfolio were developed over the course of six months. Most were created in three to four days. Some were developed in small teams with varied coding disciplines. The pages linked below narrate my contributions and thought processes. My intent is to demonstrate what I can do with my current skill set in a short period of time. Links are provided to: Jupyter Notebooks, GitHub repos, and deployed projects. Like what you see? Contact Me .
A CNN for image recognition is trained on results from Google Images API for city names. The array of probabilities provided by a softmax output layer are examined to determine subtle similarities between cities. The plans for a "City Vibes" swiping app are outlined in detail.
Supervised Machine Learning models are trained on combined data from CalTech and STScI to identify probable planet-baring stars in NASA's TESS satellite light-curve data.
A search engine for finding Simpsons quotes using a k-Nearest Neighbors model deployed as a flask API. An attempt to teach a Neural Net to generate English sentences from the opus of Homer Simpson.
Using Supervised Machine Learning on data from the Redcross to determine community risk factors for Ebola infection.
A simple data sorting model and interactive data visuals are integrated into a larger project on a team with four distinct disciplines.