ECE 47300 - Introduction to Artificial Intelligence

Note:

Compter Engineering students are allowed to count this course OR ECE 57000 Artificial Intelligence toward CmpE Selective credits. If both are taken, one will count as a CmpE Selective and the other will count as a Complementary Elective.

Course Details

Lecture Hours: 3 Credits: 3

Counts as:

  • EE Elective
  • CMPE Selective

Normally Offered:

Each Spring

Campus/Online:

On-campus only

Requisites:

ECE 36800

Catalog Description:

The course introduces the fundamental areas of artificial intelligence: knowledge representation and reasoning; machine learning; planning; game playing; natural language processing; and vision.

Required Text(s):

  1. Artificial Intelligence: A New Synthesis , Nils Nilsson , Morgan Kaufman , 1998 , ISBN No. 1558604677
  2. Purchase of a custom reference notebook may be required

Recommended Text(s):

None.

Learning Outcomes:

A student who successfully fulfills the course requirements will have demonstrated:
  1. a practical and theoretical understanding of uninformed and informed machine search and machine learning techniques. [1,2,6]
  2. a basic familiarity with the mathematics of knowledge representation. [1]
  3. an acquaintance with the fundamental difficulties involved in designing intelligent programs. [1,4]
  4. knowledge of key previous work in a broad range of artificial intelligence subareas. [1,4]
  5. an ability to apply AI techniques both in analytical and in programming contexts to solve problems, and to communicate the result of such application. [1,2,3,4,6]

Lecture Outline:

Lectures Topics
1 Introduction to AI
5 Search - review of basic search techniques - heuristic search - game playing - constraint propagation
7 Machine Learning for Classification - learning theory - decision tree learning - neural nets
8 Knowledge Representation - semantic networks, frames - pattern matching, unification - representation of action - representational challenges
3 Uncertainty - review of probability theory - compactly represented distribution - inference in compact distributions
6 Planning - STRIPS representation - solution strategies: graphplan - uncertainty: Markov decision processes
2 Machine Learning About Action Dynamics - temporal difference learning - reinforcement learning, Q learning
5 Natural Language Processing - grammars and parsing - language understanding - language generation
5 Vision - low level vision & segmentation - constraint propagation - line labeling - matching
3 Tests/Review

Assessment Method:

none