Machine Learning

Machine learning, speech/language/bioinformatics/music, submodularity & discrete optimization

Computer vision, machine learning

Convex optimization; systems and control theory

Robotics, artificial intelligence, activity recognition

Computational health, AI for sound, networks, bio-robotics, wireless, mobile and ubiquitous computing, sensing, security and privacy

Machine learning, active learning, reinforcement learning

Computational biology - precision medicine, network biology, genetics of complex traits; Machine learning - interpretability, feature selection, structure learning

Statistical learning algorithms

Development of machine learning techniques for molecular biology

Signal and image processing

Computational neuroscience, artificial intelligence, brain-computer interfaces

Computer vision, multimedia retrieval, biomedical informatics

Intelligent control in biology and engineering

Sasha Lambert works with professor Byron Boots on developing and applying algorithms for perception and imitation learning. These approaches are being tested for off-road autonomous driving as well as and robot manipulation.

Steve Mussmann works with Kevin Jamieson and Ludwig Schmidt on active learning and adaptive data collection, both from theoretical and empirical angles. Steve is especially interested in designing data collection methods that are efficient enough to power new settings and applications of machine learning. Currently, Steve is interested in understanding active learning for distribution shift and exploring the fundamental possibilities and limitations of active learning. Steve has a Ph.D. in computer science from Stanford University.

I am excited about projects where engineering solutions meet medical needs, specifically those that enable individuals with disabilities interact with the world around them in a more inclusive environment. In the past, I have worked on developing affordable and customizable orthotic devices for individuals with spinal cord injuries and attempted to simplify control methods for complex prosthetic hands. As a postdoc at UW, I hope to harness the advancements in metamaterials and smart textiles to create custom solutions for assistance and rehabilitation needs of individuals with disabilities.

Michael Regan works with professor Yejin Choi studying cognitive semantic approaches to the modeling of causal structure in language. His research focuses on creating datasets for model evaluation across a variety of tasks (e.g., schema induction, causal reasoning), problems in event, narrative, and dialogue understanding, and functional approaches to studies of language which hold that physical models of the world shape both human cognition (e.g., intuitive physics) and linguistic constructions, form-meaning pairs where meaning is assumed to be causal. He holds a Ph.D. from the University of New Mexico.

I am interested in applications of Deep Learning and Machine Learning in Genetics. We are trying to learn gene regulatory models from large-scale sequencing data to characterize the genetic sequences that determine molecular phenotypes. We focus on model interpretation to gain a better understanding of the underlying biological mechanisms that control changes in gene expression, and to identify the main trans-acting factors that are involved in these regulatory processes, such as transcription factors and RNA-binding proteins.

I am an incoming (Fall 2023) Assistant Professor in the Robotics Institute at CMU. I completed my Ph.D. in 2022 from Caltech. I am broadly interested in the intersection of machine learning and control theory, spanning the entire spectrum from theory to real-world agile robotics.

Wenya is a research fellow in Paul G. Allen School of Computer Science and Engineering at the University of Washington, advised by Noah Smith and Hanna Hajishirzi. Her research interests lie in deep learning, logic reasoning and their applications in natural language processing, e.g., information extraction, natural language understanding etc.

Sean Welleck is a Postdoctoral Scholar at UW, working with Yejin Choi. His research interests include deep learning and structured prediction, with applications in natural language processing. He completed his Ph.D. at New York University, advised by Kyunghyun Cho and Zheng Zhang, and obtained B.S.E. and M.S.E. degrees from the University of Pennsylvania. His research has been published at ICML, NeurIPS, ICLR, and ACL, including two Nvidia AI Labs Pioneering Research Awards.

Xinyi Zhou is a postdoctoral scholar working with Allen School professors Tim Althoff and Amy Zhang. Her research interests are broadly in the intersection of data mining, machine learning, and social computing. Her research has and will continue striving to bridge the gap between social theories and (multimodal) ML/AI techniques to comprehend and improve the online information ecosystem that can breed misleading, untrusted, biased, threatening, insecure, and distracting messages.

I'm interested in natural language understanding. My research is aimed at learning to automatically map natural language sentences to graph representations of their meaning, ideally in a way that works well for a broad variety of domains and languages.