Limits of Machine Learning
Discovering the Limits of Machine Learning
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
Mentor: Professor George Montañez
George D. Montañez is the Iris and Howard Critchell Assistant Professor of Computer Science at Harvey Mudd College. He holds a PhD in machine learning from Carnegie Mellon University, an MS in computer science from Baylor University, and a BS in computer science from the University of California-Riverside. Prof. George previously worked in industry as a data scientist (Microsoft AI+R), software engineer (Prestige Software), and web developer (360 Hubs, Inc.). His current research explores why machine learning works from a search and dependence perspective and identifies information constraints on general search processes. He is the director of the AMISTAD Lab.