This Year's Projects
Overview
HMC's 2022 Summer REU projects span theoretical, practical, experimental, nd human-centered elements of computer science research.
For information about our mentors, please see the Mentors link on the left side bar or just click here.
Project: Spatiotemporal Information in Human and Computer Vision
Mentor: Calden Wloka
Geirhos et al. (2018) demonstrated that popular CNNs trained on static images from ImageNet have a strong tendency to be biased toward object texture over object shape, a focus which contrasts strongly with human behaviour. They further demonstrated that when training was modified to force networks to incorporate shape cues more strongly they could improve accuracy and robustness. To my knowledge , no similar analysis has been conducted for the information focus in spatiotemporal models. This project will compare the spatiotemporal focus of information in deep networks to the spatiotemporal allocation of attention by human observers (measured through eye tracking). Action recognition is a popular problem focus for the development of spatiotemporal vision models, with a number of models developed over the past several years which demonstrate impressive performance on standard benchmarks of short action videos, and will therefore be an ideal domain to start this exploration.
Scheduling:
May 16 2021 to July 22 2021
Number of positions available:
We are looking for 1 student for this project.
What makes for a good experience on this project?
Students interested in human and computer vision systems are encouraged to apply!
Project: Design + Programming Languages + Shakespeare
Mentor: Professor Ben Wiedermann
The goal of this project is to create a tool that allows people to explore Shakespeare’s texts. Potential users of this tool include theatre professionals (such as actors, directors, and stage managers) and digital humanists (researchers who are interested in exploring the texts).
To create the tool, we will need to develop new ideas for user-interaction and new compiler-based techniques for searching through structured text. The results will be applicable beyond Shakespeare’s texts.
If you are interested in design and / or the implementation of programming languages, this project is for you!
Scheduling:
Participants may start on May 16, May 23, or May 31. We will spend 10 weeks on the project.
We will probably do most of our work over Zoom.
Number of positions available:
We are looking for 1 student for this project.
What makes for a good experience on this project?
This project is a great match for a visual artist student who is interested in CS and user interaction. In that case, the bulk of the work will be to design interactions in the app. Alternatively, the project is a great match for someone with significant CS experience (web-programming a plus!) and interest in applying Compilers research to users who might not consider themselves to be programmers. In this case, the bulk of the work will be researching and implementing ways to automatically generate queries over structured data.
Project: Discovering the Limits of Machine Learning
Mentor: Professor George Montañez
The AMISTAD lab (Artificial Machine Intelligence = Search Targets Awaiting Discovery) is a lab focused on pursuing foundational theoretical work in machine learning from a search and information theory perspective. This involves formalizing areas of machine learning as either searches or communication problems, and proving results related to machine learning, information theory, and search within those frameworks. The focus of the lab is on the abstract underlying structure of learning and search problems. Our projects will center on forming new perspectives of learning processes so that we can exploit those insights for smarter learning algorithms and understand something new about reality.
You'll have a lot of fun and solve tricky problems! Students typically end up with one or more publications from their projects, so summer research in our lab helps prepare you for graduate school!
Useful skills/interests: Strong preference given to students who are enthusiastic about AMISTAD Lab and have an ML/AI background. Interest in foundational issues in machine learning (i.e., in what makes ML work) and a good level of mathematical sophistication (ability to write rigorous proofs, multivariable calculus, familiarity with probability theory and statistics). Coding is useful, but for theoretical projects no coding is typically necessary. However, knowing LaTeX, or being willing to learn, is a must.
Scheduling:
May 16 to July 22, 2020
Number of positions available:
We are looking for 2 to 4 students for this project.
Before applying, please check out some relevant publications.
Direct links to PDFs for each of these papers is on our publications page.
- The Famine of Forte: Few Search Problems Greatly Favor Your Algorithm
- The Futility of Bias-Free Learning and Search
- The Bias-Expressivity Trade-off
- The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity
Project: Time, Path, and Cognitive Complexity of code
Mentor: Professor Lucas Bang
How complex is a piece of code?
To answer that question, we first need to decide what the word "complexity" means! One option is time complexity, or a measure of the number of steps executed by the algorithm that the code implements. Another measure is called path complexity, which gives the number of different execution paths through a given piece of code. Yet a third measure is the cognitive complexity: the amount of mental effort required to understand some source code. In this project, we will examine how time complexity, path complexity, and cognitive complexity of code are related to one another.
Scheduling:
May 16 2021 to July 22 2021
Number of positions available:
We are looking for 1-2 student for this project.
What makes for a good experience on this project?
If you are interested in any or all of human learning, programming, algorithms, and combinatorics please apply!
See here for a short video on our path complexity work from previous summers.
