Experiences in teaching neural fuzzy systems at TUCS Robert Fullér ∗ Department of Computer Science, Eötvös Loránd University, Budapest 1 TUCS Graduate School The Graduate School of Turku Centre for Computer Science (TUCS) offers a programme for gaining the Doctoral (Ph.D.) degree in Computer Science. It is open for students from everywhere. The teaching language of the school is English. Prerequisites are either a Bachelor’s or a Master’s degree in Computer Science or in a closely related field. Study time is expected to be 6 years when starting from Bachelor’s level and 4 years from Master’s level. Turku Centre for Computer Science (URL: http://www.utu.fi/org/tucs) co-ordinates Master and Doctoral level education as well as research in Computer Science among the three universities in Turku; University of Turku, Åbo Akademi University and Turku School of Economics and Business Administration. Presently there are 11 professors and around 30 other Ph.D. level researchers in Computer Science at TUCS. The Graduate School offers advanced level courses in Computer Science and supervision of students within existing research projects. The main areas of research are • Theoretical Computer Science • Algorithmics • Software Engineering • Information Systems Students are expected to take courses from at least two of these areas. Each student is assigned a supervisor from one of the fields indicated above. TUCS and its Graduate School are situated in the Turku Technology Center. The Computer Science departments of the three universities in Turku are all located in this center, together with a number of other university departments in Biology, Biochemistry, Physics and so on. The center also houses a large number of high-tech companies in Computer and Communication Technology, Electronics, Biotechnology and Material Sciences. The Technology Center provides a fertile research environment with ample opportunities for collaboration between industry and the academia. ∗ Presently post-doc visiting researcher at Institute for Advanced Management Systems Research and TUCS, Åbo Akademi University, Finland 1 2 Studies at TUCS The curriculum for the degrees of Master of Science, Master of Business Administration and the Doctor of Philosophy follow the Finnish standard requirements. The Master’s degree requires 40 credits in addition to the B.Sc. exam. Part of these credits are obtained by taking courses and part by writing a Master’s thesis. The Ph.D. degree normally requires a Master’s degree. In addition, the student has to get an additional 40 credits in the form of courses and do research leading up to a Ph.D. thesis. A standard course, covering approximately 50 hours of lectures, 20 hours of assignments in class and a smaller project assignment will usually give 5 credits. There are also smaller courses and seminars, giving 1-3 credits. 3 Neural Fuzzy systems There are several research groups at TUCS (Programming Methodology, Strategic Information Systems Planning, Theory Group: Mathematical Structures in Computer Science, Computational Intelligence for Business, Intelligent Technologies, Coding Theory, Algorithmics, Probabilistic Algorithms and Software Quality, Information Systems Research) and 29 different courses for Spring 1995. One of the courses is called Neural Fuzzy Systems which is being delivered by the author. Neural fuzzy systems are artificial neural networks with fuzzy input/output information. The (30 hours, 5 credits) course consists of three parts: The first part surveys the most often used methods of approximate reasoning and fuzzy rule-based systems. The second part covers learning algorithms of feed-forward supervised multi-layer neural networks and Kohonen’s algorithm for unsupervised learning. The third part includes learning algorithms of nero-fuzzy networks. A large number of applications of neuro-fuzzy systems to diagnostics, control and decision support is being presented. My experiences show that students are primarily interested in practical applications of neural fuzzy systems in business (finance, marketing, operations), decision support systems, computer vision and pattern recognition. 2