There are still a few seats open in the short course. We added mini-workshops in R, new trends, and animations to enrich the course.
Process Data Analytics and Machine Learning Short Course – Updated Notice
April 30 - May 1, 2018
Prof. S. Joe Qin
Texas-Wisconsin-California Control Consortium
Department of Chemical Engineering and Material Sciences
University Southern California, Los Angeles, CA, U.S.A.
[log in to unmask]<mailto:[log in to unmask]>
l Introduce the state of the arts in machine learning and applications.
l Mini-workshops on analytics methods using R, which is free license, and no knowledge of R is required.
l Topics ranging for basic concepts to advanced issues; at the end of each topic there will be introduction of the current trend and hot issues.
l Concepts and methods are demonstrated with simple and relevant examples and animated for visualization.
Analyzing large data sets has become a key basis of competition, underpinning new waves of productivity growth and innovations, according to a report by McKinsey’s MGI (2011). In a recent report again by McKinsey (2016), Buried treasure: Advanced analytics in process industries, states that, “The full power of advanced analytics requires not only acquiring new technology and analytics solutions, but also helping people improve their expertise and adopt new ways of working”.
The Process Data Analytics and Machine Learning Short Course aims to introduce to the participants a suite of recently developed data science and machine learning tools that have strong applicability to process data analysis, monitoring, troubleshooting, feature discovery and inferential sensing. Course participants will learn these tools through lectures and mini-workshops. Computer routines will be provided for these mini-workshops. The covered topics include
1 Introduction to Process Data Analytics
2 Unsupervised Learning
2.1 Principal component analysis
2.2 K-means clustering
2.3 Hierarchical clustering
2.4 Discrete or categorical data analysis
2.5 Dynamic component analysis
2.6 Process monitoring, diagnosis, and troubleshooting tools
3 SUPERVISED LEARNING
3.1 Linear discriminant analysis
3.2 Support vector machines
3.3 Partial least squares
3.4 Canonical correlation analysis
3.5 Dynamic canonical correlation analysis
3.6 Regularization via ridge regression, lasso, elastic nets
3.7 Neural networks – deep learning
4 ADDITIONAL TOPICS
4.1 Causality analysis
4.2 Kernel methods for nonlinear analytics
4.3 Case study: visualization, interpretation, and diagnosis
About The Instructor
Dr. S. Joe Qin is Professor at the Viterbi School of Engineering of the University of Southern California. He has nearly 30 years of research, industrial and teaching experience in process modeling, data analytics, and control. His research interests include process data analytics, machine learning, process monitoring and fault diagnosis, model predictive control, system identification, building energy optimization, multi-step batch process control, and control performance monitoring. He is one of the most recognized process data science experts in the world with many impactful contributions to the area of process data analytics.
Dr. Qin is a Fellow of IEEE and Fellow of the International Federation of Automatic Control (IFAC). He is a recipient of the National Science Foundation CAREER Award, the 2011 Northrop Grumman Best Teaching award at Viterbi School of Engineering, the DuPont Young Professor Award, and Halliburton/Brown & Root Young Faculty Excellence Award. He is currently a Subject Editor for Journal of Process Control and a Member of the Editorial Board for Journal of Chemometrics. He has published over 140 papers in SCI journals or book chapters, with over 10,000 Web of Science citations and an associated h-index of 49.
Who Should Attend
l Process engineers interested in learning data science and process data analytic tools.
l Managers interested in understanding where and how these analytics tools can bring benefits and competitive advantages to your organization.
l Corporate or national lab researchers interested in learning process-oriented data science applications.
Time: April 30 – May 1, 2018, 8:30 am to 5:30 pm.
Venue: Conference Room 207, The Radisson Hotel LA Midtown at USC
Address: 3540 S Figueroa St, Los Angeles, CA 90007
Lodging: Radisson Hotel Los Angeles Midtown at USC
USC Rates: Single/Double: $179 (while available). Use code tommy to make reservations online or call 800-395-7046 or Jane Gollayan-Valerio | t.213.748.4141 EXT. 1384 | [log in to unmask]
The fees for taking short course are as follows:
$1,800/p for members of the Texas-Wisconsin-California Control Consortium (TWCCC);
$1,900/p for others.
The fees include all instructional materials, continental breakfast, refreshment, and lunch for each day. All proceeds go to the University of Southern California
ESVP: Open www.usc.edu/esvp<http://www.usc.edu/esvp> and use the code twccc18sc to register.
Capacity: The maximum capacity is 20 to give full attention to each participant.
If you need specific information please contact Ms. Yuan Jin at [log in to unmask]<mailto:[log in to unmask]>. ?
Joe Qin, Professor
IEEE Fellow, IFAC Fellow