New Machine Learning Methods for Biological Data Analysis

Speaker: Prof. Olgica Milenkovic
Affiliation: University of Illinois, Urbana Champaign

Abstract: The last decade has witnessed significant developments in multiomics data acquisition technologies as well as a surge of interest in computational tools for analyzing the generated datasets. Despite these advances, many computational methods in use today are based on algorithms that produce results that are hard to interpret and may be unsuitable for the sample set formats and constraints at hand. Furthermore, many datasets are prohibitively large to be stored by individual users and require online processing, streamed computation or specialized dimensionality reduction techniques. To illustrate these points, we describe new hypergraph learning techniques for hierarchical biological network clustering and similarity search, convex online matrix factorization techniques for single cell RNA-seq data and, if time permits, inception-based deep learning methods for associating RNA expression and promoter methylation site patterns and contexts. All these methods come with analytical guarantees and offer significant performance improvements compared to existing approaches.

Biography: Olgica Milenkovic is a professor of Electrical and Computer Engineering at the University of Illinois, Urbana-Champaign (UIUC), and research professor at the Coordinated Science Laboratory. She obtained her MS Degree in Mathematics in 2001 and PhD in Electrical Engineering in 2002, both from the University of Michigan, Ann Arbor.  Prof. Milenkovic heads a group focused on addressing unique interdisciplinary research challenges spanning the areas of algorithm design and computing, bioinformatics, coding theory, machine learning and signal processing. Her scholarly contributions have been recognized by multiple awards, including the NSF Faculty Early Career Development (CAREER) Award, the DARPA Young Faculty Award, the Dean’s Excellence in Research Award and several best paper awards. In 2013, she became a Willett Scholar and UIUC Center for Advanced Study, while in 2018 she became an IEEE Fellow. In 2015, she served as Distinguished Lecturer of the Information Theory Society.

For more information, contact Prof. Danijela Cabric (danijela@ee.ucla.edu)

Date/Time:
Date(s) - May 28, 2019
1:00 pm - 2:00 pm

Location:
EE-IV Shannon Room #54-134
420 Westwood Plaza - 5th Flr., Los Angeles CA 90095