NEXT is a computational framework and open-source machine learning system that simplifies the deployment and evaluation of active learning algorithms that use human feedback, e.g. from Mechanical Turk. The system is optimized for the real-time computational demands of active learning algorithms and built to scale to handle a crowd of workers any size. The system is for active learning researchers as well as practitioners who want to collect data adaptively.

The goal of this project is to implement overconvergent modular symbols and families of overconvergent modular symbols in Sage. It can be used to compute explicit examples of p-adic L-functions.

Working alongside Nathan Clement and Leland Jefferis (two fellow grad students) I created Bee-Line, an Android educational puzzle game. The goal in Bee-Line is to help Beatrice the bee find a path through a garden of flowers. As the paths get longer the challenge and fun increases! Bee-Line has recieved over 2000 downloads on the Google Play store. The art, music, puzzle concept and storyline are completely original. Check it out!

In the fall of 2012, I went to Music Hack Day with Jordan Ellenberg and Andrew Bridy where we used the Million Song Database to create our own composition based on the Markov Music Machine! You can see our demo here. We also worked on a problem trying to cluster songs in the dataset using Echo heatmaps of Echo Nest features, and entered in a related Kaggle competition (we got 12th place!).