Three machine learning short courses will be held in parallel on Sunday, June 9 from 3 to 5 p.m. They are open to attendees of both the Women in Data Science Workshop and the Machine Learning in Science and Engineering conference.

Instructors


Introduction to Bayesian Analysis by Yao Xie Chen

Bio: Yao Xie is an assistant professor and the Harold R. and Mary Anne Nash Early Career Professor in the H. Milton Stewart School of Industrial and Systems Engineering at the Georgia Institute of Technology. She received her Ph.D. in Electrical Engineering and a minor in Mathematics from Stanford University in 2011. Prior to joining Georgia Tech in 2013, Xie worked as a research scientist at Duke University. Her research interests are statistics, signal processing, and machine learning.

Xie received a National Science Foundation CAREER Award, 2017. In 2015, she received the best student paper award at the Annual Asilomar Conference on Signals, Systems and Computers. Additionally, she was a finalist for the best student paper award at the 2007 ICASSP Conference.

Course Abstract: Bayesian analysis is a statistical procedure that endeavors to estimate parameters of an underlying distribution based on the observed distribution. It is one of the foundations of modern statistical modeling and computing. In this short
course, we will talk about the basics of Bayesian analysis, from modeling using Bayesian priors, to computing using MCMC, such as Metropolis-Hastings algorithm, Gibbs sampling, and some convergence analysis. 


Introduction to Deep Neural Networks by Zsolt Kira

Bio: Zsolt Kira is an assistant professor in the School of Interactive Computing at the Georgia Institute of Technology, branch chief of the Machine Learning and Analytics group at the Georgia Tech Research Institute (GTRI), associate director of Georgia Tech’s Machine Learning Center, and a core faculty member of the Institute for Robotics and Intelligent Machines at Georgia Tech.

His work lies at the intersection of machine learning and artificial intelligence for sensor processing, perception, and robotics, emphasizing the fusion of multiple sources of information for scene understanding. His recent projects and interests relate to moving beyond current limitations of machine learning to tackle lifelong/continual learning and adaptation as well as distributed perception across heterogeneous robot/sensor teams.

Kira has grown a portfolio of projects funded by NSF, DARPA, and the IC community. Additionally, he has published more than 30 papers in these areas, received several best paper/student paper awards, taught several graduate and undergraduate machine/deep learning courses at Georgia Tech, and has been invited to speak at related workshops in both academia and within the DoD.


Machine Learning with TensorFlow by Rasmi Elasmar

Bio: Rasmi Elasmar is an engineer at Google based in New York.

Course Abstract: In this course, we will work through a scientific problem using scalable machine learning tools, including TensorFlow and various Google Cloud technologies. A general familiarity with machine learning and Python programming is helpful, as this course will focus on tackling the engineering constraints behind large-scale machine learning. This will be an interactive course and materials will be made available online. A laptop will be helpful but not necessary.