Machine Learning Short Courses
All short courses will be held in the Hillman Center (building 9B on the CMU campus map):
https://www.cmu.edu/assets/pdf
Machine Learning Bootcamp
Time: 9-11:30 am, June 6
Location: Gates-Hillman room 4401 (Rashid Auditorium)
Instructors: Prof. Jeff Schneider (CMU), Prof. Aarti Singh (CMU), Dr. Kirthevasan Kandasamy (CMU)
Description: This short course will be taught by Prof. Jeff Schneider, Prof. Aarti Singh, and PhD candidate Kirthevasan Kandasamy from the CMU Department of Machine Learning. The course will provide an overview of how machine learning is applied to science and engineering problems, followed by in-depth discussions of active learning approaches to real-time experimental design and bandit models, which are used across science and engineering in a diversity of optimization problems. Attendees do not need to bring their laptops but are welcome to do so.
Large-Scale Machine Learning with TensorFlow and the Cloud
Instructor: Rasmi Elasmar (Google)
Time: 9-10:00 am, June 6
Location: Gates-Hillman room 4303
Description: This short course will be taught by Rasmi Elasmar from the Google office in New York City. 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, so please bring a laptop to follow along.
Machine Learning in Materials Research
Instructors: Dr. Gilad Kusne (NIST), Dr. Daniel Samarov (NIST)
Time: 9-11:30 am, June 6
Location: Gates-Hillman room 4405
Description: This short course will be taught byDr. Gilad Kusne and Dr. Daniel Samarov from NIST. The bootcamp consists of three hoursof lectures covering a range of data analysis topics from data pre-processing through advanced machine learning analysis techniques with a focus on applications in materials research. Attendees will learn to analyze a range of data types from scalar properties such as material hardness to high dimensional spectra and micrographs. Attendees do not need to bring their laptops but are welcome to do so.