CS4793 "Introduction to Artificial Neural Networks"
Syllabus
Instructor: Dr. Razvan Andonie
Office: SB 3.02.01 E
Office
hours: Monday, Wednesday
Phone: 458-5689
Textbook: M. T. Hagan, H. B. Demuth, M. Beale, "Neural Network Design", PWS Publishing Co., Boston, 1996.
Prerequisite: CS3793 Introduction to Artificial Intelligence.
COURSE DESCRIPTION AND OBJECTIVES
This course introduces the foundations of artificial neural networks. Conventional (von Neumann) computing, which has dominated information processing for nearly half a century, is based on decision rules and algorithms encoded into the form of computer programs. The algorithms and program-controlled computing necessary to operate convential computers have their counterpart in the learning rules and information recall procedures of a neural network. These are not exact counterpart, however, because neural networks go beyond digital computers since they can progressively alter their processing structure in response to the information they receive. The objectives of this course are to give you an understanding of artificial neural networks and how they are realized by computer programs.
GRADING
Grading is be based on programming assignments and two take-home exams. The assignments are implementations/simulations of neural models in C++, Matlab, or SNNS (Stuttgart Neural Network Simulator). The exams will be announced two weeks in advance.
WEB LINKS
DSI Neural Networks Group
is a very complete source of electronic information.
At www.shef.ac.uk/psychology/gurney/notes/
you can find a set of non-mathematical notes that help you to learn about the
basic concepts and ideas in Artificial Neural Networks.