Wednesday 1:00 PM- Thursday 12:00 PM
Machine Learning on Big Data
Instructor: Kao-Tai Tsai
Course Description
Technical advancement in big data generation necessitates the data analytical skills to extract important tactical information more critical than ever. By taking advantages of advanced computing technologies and modern statistical research, machine learning has becoming one of the most sought-after capabilities in big data analysis to meet such challenges. Machine learning methodologies have broad applications and have been implemented in discovering precision medicines, advancing scientific research, and helping commerce in market segmentation and targeted product development.
What will be discussed:
o Part 1: general philology of data analysis according to Professors Tukey and Huber, and data quality related to big data.
o Part 2: exploring data structures and distributions using graphical tools and recursive partitioning methodologies.
o Part 3: supervised regression and classification methods including lasso, elastic-net, support vector machine, etc.
o Part 4: non-supervised methods including clustering, principle component analysis, corresponding analysis, etc.
o Part 5: case studies with genomics data and commercial data.
Who should attend: statisticians and data scientists in all industries with data analysis experience and knowledge of programming language such as R, SAS, or Python. (Note: course examples of data analyses will be illustrated using R.)
