Educational Objectives
Graduates will be able to:
- Identify data streams typically found in pharmaceutical organizations (but can be extended to other industries) that will benefit from the adoption of Machine Learning and the corresponding dissemination of results to improve and streamline the quality of decision making.
- Organize teams to develop machine learning algorithms targeted to specific workflows aimed at increasing access and adoption of sophisticated analysis.
- Diagnose existing Data Science workflows for potential improvements in reliability, efficiency and speed.
- Explore and evaluate the adoption of state of the art machine learning models to address pharmaceutical development problems in the organization or improve on existing tools.
Educational Outcomes
Students will be able to:
- Understand and explain the underlying concepts powering relevant Machine Learning algorithms that will be covered throughout the program.
- Understand and explain the applicability of the most frequently used loss functions for model fitting problems.
- Identify appropriate Machine Learning algorithms to solve problems relevant to pharmaceutical development and rigorously evaluate the available data sets for applicability by applying tools in data visualization analysis and feature engineering.
- Relate between sequential decision problems and decision trees, Bayesian networks and other Bayesian models arising in statistical learning and incorporate the model uncertainty in the underlying decision.
- Apply reproducible research and version control to efficiently manage Machine Learning projects in a collaborative environment in situations and organizations typically found in industry.
SEE REQUIRED COURSES & Descriptions
Instructors
Dr. Zhong Xiao, Lecturer, Department of Mathematical Sciences
Xiao Sophia Zhong holds a Ph.D. in Computer Science and Technology from Zhejiang University, China, and a Ph.D. in Mathematics with emphasis on Statistics from Missouri S&T. She worked at AstraZeneca R&D Boston, Whitehead Institute of MIT, and Tsinghua University, China. Her research focuses on artificial intelligence, pattern recognition, data mining, financial engineering, statistical applications, and simulations.
Dr. Darinka Dentcheva, Professor, Department of Mathematical Sciences
Darinka Dentcheva holds a Ph.D. and a Doctor of Sciences (Habilitation) degree from Humboldt University Berlin, Germany. Her current research interests are in optimization under uncertainty and risk. She is passionate about education and has participated in the development of new graduate curricula and courses. She is Associate Editor of several scientific journals, a member of international scientific bodies, and a recipient of multiple research awards and recognitions.
Dr. Jose Tabora, Bristol-Myers Squibb
Jose Tabora holds a Ph. D. from the University of Virginia. For the past 25 years he has worked for Merck, Eli Lilly and BMS in Pharmaceutical product Development. Through his professional life he has championed the adoption of machine learning and data science in various workflows of pharmaceutical process development. He is a Fellow of the AIChE.
Dr. Jacob Albrecht, Bristol-Myers Squibb
Jacob Albrecht is a Principal Scientist in Product Development at Bristol-Myers Squibb, with a Ph.D. in chemical engineering from MIT. With over a decade of pharmaceutical development experience, he has championed the adoption of modern approaches to data science and machine learning both within BMS and through pharmaceutical industry consortia.
Program Contact:
Professor Adeniyi Lawal
Office: 100A McLean Main
Phone: 201.216.8241
Email: [email protected]
