An event creates several types of data. In a biological process the generated data comes in the form of sequences, pathways, images, etc. Furthermore, there are associated sources such as publications and web pages. One emerging field in analysis is concerned with the ability to associated and mine data from these multiple domains.
This course will consider data from several domains (sequences, images, text, PDFs, etc.). This course will consider current algorithms in performing intra-domain associations. These are methods concerned with single domain data.
This course will progress to consider linkages between the domains inter-domain linkages and methods to represent data from different domains. Finally, this course will consider multi-domain methods of clustering, data association, and data space stress.
Students will be familiar with a programming language such as Python or Matlab. Experience with C++ and Java will also be acceptable.
There is no textbook for this emerging technolgy class. We will use recent publications from many fields.
This course will not be a traditional lecture course. Grading will rely heavily on a semester project and in-class participation. Students will be required to make mini-presentations during the semester and a project presentation at the end of the semester.
Students interested in this class and needing more information should contact.
Jason M. Kinser
703 993 3785
jkinser@gmu.edu