Ben Kizaric
Subspace Clustering for interpretable, semi-supervised machine learning tasks; Image Compression.
Machine learning uses algorithms to build analytical models, helping computers “learn” from data. It can now be applied to huge quantities of data to create exciting new applications. Researchers at WID are developing new methodology and theory for extracting useful information from data which may be noisy or high-dimensional, contain missing elements, or come from a variety of different sensors or streaming input.
Machine learning at WID plays a key role in problems as diverse as understanding the immune system, finding the funniest cartoon captions, and developing driverless cars.
Machine learning is an important component of WID’s Data Science Hub.
Subspace Clustering for interpretable, semi-supervised machine learning tasks; Image Compression.
Neural network models on soil micobiome data to predict characteristics of potato growth.
Designing practical, data-efficient algorithms with rigorous guarantees for statistical applications
Continuous optimization for machine learning, reinforcement learning and other data science problems
Data Science Facilitator
Facilitating connections and training researchers in data science.
Institute for Future Edge Networks and Distributed Intelligence (AI-EDGE) led by Robert Nowak, UW–Madison professor of electrical and computer engineering and researchers at Ohio State.
Relationship between genomes and their environments to predict organisms' fitness correlations.
Large scale and robust optimization in machine learning, min-max problems with game theory