In a day and age where many consider deep learning an off-the-shelf solution to any and all classification/prediction problems, it's important that people examine whether their neural network models are vulnerable to targeted attacks. This project implements a framework for generating adversarial examples: input data crafted to cause the neural network to produce unexpected or targeted incorrect behavior.

Many significant works of Latin poetry follow the format of dactylic hexameter, meaning that each line is composed of some combination of six metrical feet, each of which is either two long syllables or a long syllable followed by two short syllables. Scansion is the process of identifying the pattern of syllable lengths. Through this project, I use machine learning to scan lines of Latin poetry in dactylic hexameter.

The goal of this computational project is to analyze squash game footage by tracking the ball and the movements of the players. The objectives include printing the positions of the ball and players at any specific moment and displaying the trajectories of the ball and the players. From the footage of a squash game, I am able to extract the positions of the players for all frames and the position of the ball for almost 70% of the frames.

In this project, I worked with polycubes: 3D tiles formed from a set of n cubed tiles. My goal was to write a function to calculate the number of distinct polycube forms possible given a set of n cubes and present a visual representation of the set obtained. To achieve my goal, I focused on the optimization of any algorithms used in order to handle the maximum possible value n in a reasonable time frame.