machine-learning

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the models' …

Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed …

Adversarial Training against Location-Optimized Adversarial Patches

A fast crowdsourced vote aggregation algorithm

Research Internship at the University of Tokyo in the summer of 2018

Research Internship at Robert Bosch in the summer of 2017

Many real world problems can now be effectively solved using supervised machine learning. A major roadblock is often the lack of an adequate quantity of labeled data for training. A possible solution is to assign the task of labeling data to a crowd, …

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