(including reports and presentations)
Research Internship at Robert Bosch in the summer of 2017
Application of momentum in second order methods, such as Newton’s method and BFGS
Implementation of the model described in “Training deep neural nets to aggregate crowdsourced responses.” by Gaunt et al.
Techniques to effectively perform multi-label classification from a very large set of labels
Loop transformation passes to obfuscate programs in LLVM IR
A program that simulates answers given by a crowd to multiple choice questions with either a single or multiple answers correct, and writes it to a CSV
Perform pixel-wise segmentation on satellite images based on land cover type