University of Wisconsin Madison Introduction to Artificial Neural Network and Fuzzy Systems (E C E 539) Syllabus Course Learning Outcomes Course Learning Outcome 1 1. Students will be able to determine if a given data analylsis task is a pattern classification problem or a model approximation problem. 2 2. Students will be able to apply multi-layer perceptron neural network training algorithm to develop artificial neural network (ANN) based pattern classifiers and data predictors. 3 3. Students will be able to apply support vector machine (SVM) to develop pattern classifiers. 4 4. Students will be able to apply radial basis function to model given data sets. 5 5. Students will be able to apply self organization map and k-means to perform clustering operations of a given data set. 6 6. Students will be able to develop a fuzzy logic controller to perform simple control task on a given data set. 7 7. Students will be able to apply stochastic optimization methods, including simulated annealing, genetic algorithm and random search to solve a discrete optimization problem. Details Introduction to Artificial Neural Network and Fuzzy Systems E C E 539 ( 3 Credits ) Description Theory and applications of artificial neural networks and fuzzy logic: multi-layer perceptron, self-organization map, radial basis network, Hopfield network, recurrent network, fuzzy set theory, fuzzy logic control, adaptive fuzzy neural network, genetic algorithm, and evolution computing. Applications to control, pattern recognition, nonlinear system modeling, speech and image processing. Prerequisite(s) Comp Sci 302, or Comp Sci 310, or knowledge of C programming lang Department: ELECTRICAL AND COMPUTER ENGR College: College of Engineering Instructor Instructor Name Instructor Campus Address instructorEmail@emailaddress.edu Contact Hours Course Coordinator YU HU Text book, title, author, and year Neural Networks: A Comprehensive Foundation, Simon Haykin, Prentice Hall, New Jersey, second edition, 1999. Supplemental Materials Required / Elective / Selected Elective Selected Elective ABET Program Outcomes Associated with this Course 1 A An ability to apply knowledge of mathematics, science, and engineering 2 B An ability to design and conduct experiments, as well as to analyze and interpret data 3 E An ability to identify, formulate, and solve engineering problems 4 J A knowledge of contemporary issues 5 K An ability to use the techniques, skills, and modern engineering tools necessary for engineering practice Program Specific Student Outcomes Brief List of Topics to be Covered Learning paradigms, perceptron learning Multi-Layer Perceptron and Back-propagation learning Pattern classification Support vector machines Clustering, Self-Organization Map, Radial Basis Network, Time series analysis, system identification and expert system applications Fuzzy Set Theory and Fuzzy Logic Control Genetic Algorithm and Evolution Computing Recurrent Network, Hopfield network (time permit) Additional Information Printed: Oct 23, 2017 1:14:50 AM Generated by AEFIS. Developed by AEFIS, LLC Copyright © University of Wisconsin Madison 2017. All rights reserved.