Jiang Bian, PhD, MS
Assistant Professor
Division of Biomedical Informatics
University of Arkansas for Medical Sciences
4301 W. Markham St. Slot 633-1, Little Rock, AR 72205
Email: jbian [at] uams.edu or jxbian [at] ualr.edu
Work: (501) 603-1779



CPSC 7373 is a graduate-level introductory course into the field of Artificial Intelligence (AI) offered in the Department of Computer Science at UALR. AI is also one of the core courses in the Bioinformatics program offered jointly by UALR and UAMS. We will start the course with introductions to some basic elements of AI, such as knowledge representation, interference, machine learning, neural networks, graph theory based network analysis, natural language processing, information retrieval, problem solving, and learning methods in general. And we will quickly dive into various specific research topics using these basic AI elements, such as social network analysis, and graph theoretical analysis of human brain connectome.

Moreover, we are now in the era of the "big data" revolution where nearly every aspect of computing engineering is being driven by large-data processing and analysis, often in real or near-real time. It is important for the students to gain exposure to big data analytic problems and applications. Especially, this class aims to give the students insight to the basics of cloud computing, and hands-on experiences with the state-of-the-art programming paradigm--MapReduce--for a cloud computing environment to address the computational requirements of the big data problem.

The design of the class does have a strong focus on bioinformatics. The applications and problems presented in the class are derived from the instructor's research in bioinformatics using AI elements, such as the study of functional human brain networks and mining social media content for public health issues.

The preliminary list of topics that will be covered in this class include, but are not limited to:

  • Problem solving - Search
  • Probability, graphical representation, and Bayes network
  • Hidden Markov models, Markov Decision Process, and Reinforcement learning
  • Machine learning (supervised, unsupervised) (e.g., support vector machines, k-mean clustering, etc.)
  • Neural networks
  • Graph theory and network analysis (e.g., human brain network organization)
  • Natural Language Processing and Information Retrieval (e.g., social network analysis)
  • Cloud-computing, Map-Reduce programming paradigm, big data analytic

The final list of topics is subjected to change based on the survey conducted at the beginning of the class, according to the students' background and interests.

Course Materials

  • Textbook: Stuart Russell and Peter Norvig. 2009. Artifcial Intelligence: A Modern Approach (3rd ed.). Prentice Hall Press, Upper Saddle River, NJ, USA. (AIAM 1e, chapter 1 and 2 are online at AIAM 1e)

General readings:



Tentative schedule of classes and assignments (will be updated regularly)