Machine Learning & Applications

17 Jan Machine Learning & Applications

Keynote Speaker

Professor Jun Zhang
Department of Electrical Engineering and Computer Science
University of Wisconsin-Milwaukee

In recent years, there has been a lot of interest in machine learning and its applications. Despite the wide variety of applications, machine learning essentially helps to solve three basic problems: classification, regression, and optimal control. In classification, the problem is to assign an input to one of a finite number of categories. For example, when the input is an X-ray image that contains a lump, classification determines if the lump is cancerous. In regression, the problem is to use the input to estimate the value of a quantity of interest. For example, given a patient’s current conditions as indicated by a number of test results, regression predicts how long (e.g., in terms of days) the patient needs to stay in the hospital (where 5.3 days is allowed). Finally, in optimal control, the problem is to find an “optimal policy” that is able to respond to a wide range of situations and maximize a performance index over time. For example, if a patient is to be treated over a period of multiple years, optimal control finds a treatment policy that, depending on the patient’s condition at various points of time, perform treatment actions in such a way that produces the maximum improvement for the patient while minimizing the total amount of time for the treatment.  In this talk, we will provide an overview on how machine learning solves the three basic problems described above. We will also describe some of our current research in machine learning.

About the speaker

Dr. Jun Zhang received his PhD degree in electrical engineering and is currently a Professor in the Department of Electrical Engineering and Computer Science. His research interest is in machine learning and its applications in medical imaging, medicine, power systems, and finance.