Machine Learning

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

Machine learning, artificial intelligence, data science

Artificial intelligence, web search

Computer vision, machine learning

Convex optimization; systems and control theory

Robotics, artificial intelligence, activity recognition

Machine learning, active learning, continuous and discrete optimization, multi-armed bandits, machine learning software systems

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

Computational and graphical methods in multivariate analysis

Artificial intelligence, human computer interaction, natural language processing

Intelligent control in biology and engineering

Nick is a postdoctoral researcher with the Taskar Center for Accessible Technology doing work in mapping and analyzing individual-level pedestrian accessibility of public spaces with graph theoretic interpretations of equity. His doctoral work involved the development of the OpenSidewalks and AccessMap projects that, respectively, define and collect open pedestrian transportation network data for a wide set of use cases and interpret that data into a user-friendly and individually-customizable web map.

Weihao Kong works with professor Sham Kakade. His research focuses on the information-theoretic side of machine learning, with the goal of developing efficient algorithms that extract accurate information from modest amounts of data under varies settings (e.g., high-dimensional, distributed, etc.). More broadly, his research interests span statistical learning, high-dimensional statistics, and theoretical computer science. He earned his Ph.D. from the Computer Science Department at Stanford University.

Amrita Mazumdar works with Luis Ceze at the intersection of computer systems and visual computing. Her recent work applies ideas from computer vision and perception to cloud software and custom hardware. She received her Ph.D. from the Allen School in 2020.

Joseph McMahan works with professor Luis Ceze and the SAMPL group on deep learning research. His current research deals with connecting the rapidly-changing demands of machine learning models with agile hardware support to enable faster and more dynamic ML development and research. His previous research has been at the intersection of computer architecture, formal methods, and security. McMahan received his Ph.D. from UC Santa Barbara in computer architecture.

Maximilian Schleich works with professor Dan Suciu of the Database group. His research lies at the interface of databases and machine learning. In particular, he investigates how the learning of models can be improved by exploiting the structure and semantics of the underlying database. Schleich received his Ph.D. in Computer Science from the University of Oxford.

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.