Date:
8:30am-4:30pm, Tuesday, May 6, 2025, Sheraton Albuquerque Airport Hotel, Albuquerque, NM
Course Objectives:
- Understand basics of data types, organization, and preprocessing.
- Learn fundamental concepts of unsupervised learning methods, their use cases, and limitations.
- Develop an appreciation for supervised learning techniques, validation approaches, and
- complex models.
Course Description:
Machine learning (ML) is a rapidly growing area in artificial intelligence (AI) that focuses on the development and utilization of statistical algorithms capable of learning from existing data and generalize to new data without explicit instruction. As such its popularity has surged in a variety of disparate fields like computer vision, cybersecurity, natural language processing, medicine, and more recently experimental sciences.
This course is designed explicitly with non-experts in mind and targets audiences interested in ML but lacking the background and exposure to ML techniques and pitfalls. The course will begin with the basics of data organization, data wrangling, and data preprocessing. We will then move on to discuss commonly used clustering methods, anomaly detection methods, and latent variable models. The course will conclude with supervised learning methods including regression, Bayesian approached, and neural networks.
Published experimental work will be used to illustrate concepts across the entire lecture series demonstrating use cases for data wrangling, unsupervised, and supervised methods.
Who Should Attend?
This course targets non-experts, and non-practitioners of ML methods, that are interested in learning the basic concepts to strengthen collaborations and better navigate ML topics in their professional duties.
Instructor: Alex Belianinov, Principal Member of Technical Staff, Sandia National Laboratories
Alex received his B.S. in Chemistry from Case Western Reserve University and his Ph.D. in Analytical Chemistry from Iowa State University working under Prof. Patricia Thiel. During his Ph.D. Alex’s research focus was on Scanning Tunneling Microscopy (STM) and X-ray Photoelectron Spectroscopy (XPS) to study thin films on semiconducting surfaces. Prior to joining the Ion Beam Laboratory at Sandia National Lab, he was a Postdoctoral Researcher at the Center for Nanophase Materials Sciences at Oak Ridge National Laboratory under Prof. Sergei Kalinin, where he worked with STM, Atomic Force Microscopy (AFM), and Scanning Transmission Electron Microscopy (STEM) to interrogate a broad range of material systems; as well as begin to apply machine learning (ML) methods to handle and process experimental data, . After his Postdoctoral appointment Alex became a strategic hire staff scientist at CNMS in the
Nanofabrication Research Laboratory group at Oak Ridge National Laboratory, continuing his work with STEM, as well as branching out to Helium Ion Microscopy (HIM), and Secondary Ion Mass Spectrometry (SIMS).
Alex’s research interests revolve around designing and building new imaging and spectroscopic capabilities for various analytical platforms like scanning probe, electron, and ion microscopes, as well as developing new experimental capabilities for particle accelerators. These capacities, coupled with machine learning techniques are then applied to study a broad range of material classes, interfaces, functional devices, and device failure modes.
Course Materials:
Course noes.