Provides a grounding in decision support systems and prepares students to design, use, and evaluate these systems in a variety of application domains. Topics covered include rule-based production systems, fuzzy logic, and data mining for knowledgeable rule generation.  Prerequisites: C.S. 2126 and I.T. 2426. (1st)

Expectations:

E1. Students have basic computer skills and familiarization with common microcomputer applications, including web browsing, email, text editing, spreadsheets, and file manipulation.

E2. Students have had College Algebra (Math-1056) or the equivalent.

Course Outcomes:

R1. Students will gain a firm grasp of rule-based knowledge base systems, and know when to apply forward-chaining and backward-chaining inference systems.

R2. Students will understand and be able to apply measures of association to measure the functional quality of proposed rules in rule-based inference systems.

R3. Students will be able to apply decision tree construction algorithms such as ID3 as a prelude to data mining.

R4. Students will have a basic grasp of unsupervised clustering techniques, including k-means clustering.

R5. Students will have a high-level understanding of fundamental AI techniques used in decision support systems, including neural networks, genetick algorithms, and fuzzy logic.

R6. Students will be able to identify key characteristics of decision situations, and use these characteristics to choose appropriate decision support techniques.