Advisor: Min Xu
Sima Behpour is a postdoctoral fellow working on continual-learning and meta-learning frameworks. The goal of her research is developing robust continual-learning algorithms for real-world problems.
She received her Ph.D. in machine learning from University of Illinois at Chicago. Her research interests lie in the intersection of machine learning, computer vision with a focus on adversarial learning, online learning and meta-learning.
Advisor: Jian Ma
Ben’s research aims to discover connections between bioimaging and genomics through computational image analysis and machine learning. Ben has applied state-of-the-art image analysis tools drawing on advances in deep learning to analyze histological images and relate nuclear and cellular features to genomic data, such as gene expression and mutation, primarily within the context of breast cancer. Ben is working to develop appropriate machine learning tools that can infer causal relationships between phenotype and genotype through such joint image-genomic analysis. Ben is also interested in extending these ideas and image analysis tools to other microscopic imaging modalities that may reveal unique genomic connections. Ben has worked on other image processing problems, such as stereo vision, and is generally interested in image and signal processing and machine learning. Ben received his B.S. in ECE from Carnegie Mellon University in 2009 and his Ph.D. in ECE from the University of Illinois at Urbana-Champaign in 2017.
Advisor: Ziv Bar-Joseph
I obtained my Ph.D. degree at the University of Central Florida in Computer Science. During my Ph.D. study, I developed computational methods for Transcription Factor binding and microRNA targeting, which are very important in transcriptional and post-transcriptional gene regulation. As a postdoc in Dr. Ziv Bar-Joseph’s group, I am carrying on my gene regulation study in cell differentiation. I am studying the genetic regulatory networks which regulate the cell differentiation process using machine learning and statistical models.
Advisor: Andreas Pfenning
The primary goal of Morgan’s research is to understand the evolution of complex behaviors through a synthesis of comparative genomics and experimental neurobiology. Morgan received her B.A. in Biological Sciences, with a specialization in Evolution & Ecology, from the University of Chicago in 2009. She earned her Ph.D. in Behavioral Neuroscience from Oregon Health & Science University in 2016. In her dissertation work, she sought to identify the fundamental genomic and molecular properties that characterize brain circuits for vocal learning, the basis for birdsong and human speech. Her efforts culminated in several high-profile publications and proposed a new model for the evolution of complex vocal behavior. In order to further this work, she is now developing methodologies to interrogate the genomic regulatory elements that drive behavioral gene expression, through a combination of large-scale computational genomic analyses and high-throughput experimental assays of gene expression. She has performed field work in North and South America and maintains a long-term interest in developing new methods for exploring neurobiological and genomics questions in field settings. She was awarded the inaugural BrainHub postdoctoral fellowship and joined the Computational Biology Department in 2016.