CSE 941 Selected Topics in Artificial Intelligence

Theme for Fall, 2003:  Mentally Developing Robots

Description

This course is designed for students who are interested in ways human mind develops and how to enable robots to develop their mental skills.   The emphasis is on the computational modeling of autonomous mental development.

Topics:
  1. Muddiness of tasks
  2. Overview of AI approaches --- knowledge-based, learning-based, behavior-based, evolutional and the new developmental approach.
  3. Human mental development, results from neuroscience and developmental psychology
  4. Overview of animal learning theories and models
  5. Supervised, reinforcement and communicative learning (how to enable robots to acquire language and learn through language)
  6. Architectures for automatic mental development
  7. Automatic generation of representation from data
  8. Sensory mapping (Laplacian of Gaussian, Gabor, wavelets filters;  principal component analysis and  independent component analysis)
  9. Attention selection 
  10. Motor mapping and robot body for mental development
  11. Cognitive mapping,  representation and its development (large multimodal database and hierarchical discriminant regression)
  12. Motivational system
  13. Unification and integration of mental capabilities through development, including vision, audition, touch, language, reasoning, decision making, planning, object manipulation and navigation (information fusion and sensor fusion)
  14. Machine autonomous thinking and its development
  15. Consciousness from mental development
  16. Examples of experimental developmental robots
  17. Applications, impacts and future directions

    For more information about this subject, read an article appeared in Science. 
Instructor: John Weng
Office: 2325 Engineering Building; phone: 353-4388; e-mail: weng@cse.msu.edu
Class: 4:20pm - 5:40pm, Mondays and Wednesdays, room 3400 Engineering Building.
Text:  Instructor prepared book manuscript
Prerequisites: Knowledge in calculus, probability, statistics and image processing or computer vision.

Course arrangement:

In this seminar course, each student will work on a related project, some homework, some seminar presentations and one project presentation.  One final examination.  3 credits.



Back To Weng's Home Page: http://web.cse.msu.edu/~weng/