For his master’s degree thesis, which also fulfilled requirements in the CSML graduate certificate, Sid Gupta compared the use of various machine learning methods to estimate probable volatility and prices for vanilla options, a type of financial derivative. In addition to neural networks, Gupta used decision tree-based ensemble models such as gradient boosted trees and random forests to estimate volatility. He used the S&P 500 option price data from 2016 to 2018 to train and test his models.

For his independent project for CSML, Jafar Howe decided to develop an English language accent classifier, basically a tool to accurately detect different English accents. Howe did this by converting speech samples into a time-frequency spectrogram, a visual representation of audio. 

Research on linear dynamical systems by Yanxi Chen, a doctoral student in Princeton University’s Department of Electrical and Computer Engineering, and H. Vincent Poor, the Michael Henry Strater University Professor, won the outstanding paper award at this year’s International Conference on Machine Learning, which was held in Baltimore, Maryland from July 17 to 23.

Caio Costa tackled computer vision for his CSML independent project, specifically how computers may perceive objects that are partially occluded from view. He set out to put together a machine learning process that uses light bounced off a surface to determine an object’s shape, a technique known as non-line-of-sight (NLOS) imaging, a burgeoning area of study in the computer vision field.