MATH 465 - Introduction to Artificial Neural Networks

(3.00)

This course gives a systematic introduction to artificial neural networks, which represent a rather new and fundamentally different approach to computing and information processing. Providing parsimonious universal approximators for static and dynamic mappings, synthetic methodologies for building models and/or solutions, abilities to learn from and adapt to environments, and massively parallel computation paradigms, the artificial neural networks have formed a powerful approach to solving nonlinear or complex problems in a broad spectrum of areas including signal speech/image processing, system control, pattern recognition, robotics, financial management, digital communication, etc. This course will cover multi-layer perceptrons, recurrent neural nets, global minimization for training, adaptive and robust neural nets, neural filtering, identification # and control, support vector machines, self-organizing maps, etc.

Course ID: 55260
Consent: No Special Consent Required
Components: Lecture
Requirement Group: You must have completed MATH 221 and MATH 251 and MATH 301 and STAT 451 all with a grade of ‘C’ or better before you can enroll in this course.