Garrett Bingham

Garrett Bingham

About Me


I am a senior at Yale University majoring in Computer Science & Mathematics. I am interested in the automatic design of neural network architectures, and more broadly in techniques for automated machine learning. I will begin my Ph.D. studies this fall.

 

Research


Preliminary Studies on a Large Face Database

Benjamin Yip, Garrett Bingham, Katherine Kempfert, Jonathan Fabish, Troy Kling, Cuixian Chen, and Yishi Wang
2018 IEEE International Conference on Big Data

MORPH-II

My contribution was discovering thousands of gender, race, and birthdate inconsistencies in the MORPH-II face image dataset that previously published research had missed. In this paper we discuss our strategy to fix these errors and release these corrections in the hope that future research utilizing MORPH-II will be more accurate.

 

Random Subspace Two-dimensional LDA for Face Recognition

Garrett Bingham

RS-2DLDA

Random Subspace Two-dimensional LDA (RS-2DLDA) is a novel machine learning algorithm that improves upon a 2D generalization of LDA in which the input data is left in matrix form instead of being vectorized. RS-2DLDA builds an ensemble of classifiers by performing k-nearest neighbor classification in subspaces defined by random selections of the feature vectors learned during training. This gives high accuracy and prevents overfitting. Applied to face recognition, RS-2DLDA outperformed similar approaches on the MORPH-II and ORL datasets.


News


Amazon

This summer I will intern at Amazon working on robotics.

One paper submitted to ACL 2019.

LILY Lab

I joined the Language, Information, and Learning at Yale (LILY) Lab under the supervision of Prof. Dragomir Radev. I worked on cross-lingual information retrieval for the IARPA MATERIAL Program.

Reservoir Labs

At Reservoir Labs, I developed techniques for speeding up neural network computations by improving a tool called R-Stream.TF. I was supervised by Dr. Benoit Meister.

AIT-Budapest

I studied computer science at the Aquincum Institute of Technology in Budapest, Hungary.

I delivered an oral presentation on RS-2DLDA at the NES Mathematical Association of America Meeting hosted by Sacred Heart University.

I gave a poster presentation on RS-2DLDA at the Council on Undergraduate Research REU Symposium at The Westin Alexandria.

University of North Carolina Wilmington

Supervised by Dr. Cuixian Chen and Dr. Yishi Wang at UNC Wilmington, I developed a new algorithm for face recognition called RS-2DLDA.

Yale University

I started my undergraduate studies at Yale University.