Plenary
Presenter:

Prof. Takeshi Yamakawa

Department of Brain Science and Engineering
Graduate School of Life Science and Systems Engineering
Kyushu Institute of Technology
2-4 Hibikino, Wakamatsu, Kitakyushu, Fukuoka 808-0196
Japan

<http://www.brain.kyutech.ac.jp/coe21/index_e.html>

Authors: Takeshi Yamakawa, Keiichi Horio and Takahiro Tanaka

Title: Advanced Learning of SOR Network Employing Evaluation-based Topology Representing Network
Abstract:

Learning systems such as multi-layer feed-forward neural networks, wavelet networks and so on need appropriate learning data (input data and teaching output data). These method are not so useful in case when we cannot get the appropriate learning data.
   Even in this case, it is not so difficult to evaluate the system output for arbitrarily applied input. The learning data of input-output pairs with their evaluations are easily obtained and thus is easily used for modeling the system. SOR (Self-organizing Relationship) network is a modeling tool which can be established by a set of input-output data and corresponding evaluation. This SOR network can act as a knowledge acquisition system and also act as a fuzzy inference engine.
   The linkage among the units in competitive layer is fixed and not flexible, and thus not used for complicated systems. In this plenary talk, the advanced learning process is presented for the original SOR network by employing evaluation-based TRN (topology representing network).  By this learning, the linkage among the units in the competitive layer can be more flexible and thus used for modeling of much more complicated systems. The application of the SOR network established by this learning process to a manipulation control is also presented.

Biography:

Takeshi Yamakawa   received the B. Eng. degree in electronics engineering in 1969 from Kyushu Institute of Technology, Tobata and M. Eng. degree in electronics engineering in 1971 from Tohoku University, both in Japan. He received the Ph.D. degree for his studies on electrochemical devices in 1974 from Tohoku University, Japan. From 1974 to 1977, he engaged in the development of new electrochemical devices as a Research Assistant at Tohoku University. From 1977 to 1981 he served as a Research Assistant in electrical engineering and computer science at Kumamoto University, Japan. From 1981 to 1989 he was an Associate Professor at Kumamoto University. He joined the faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology (KIT), Iizuka, Japan and received a full professorship in April 1989. He established a foundation, Fuzzy Logic Systems Institute (FLSI), in Japan in 1990 to promote the international collaboration on fuzzy logic, neural networks and soft computing, and to promote the spread of the research results. He is now the chairman of FLSI and the dean of Computer Science and Systems Engineering in KIT, Iizuka. His main research interest lies on hardware implementation of fuzzy systems, fuzzy neural networks, and chaotic systems. He developed fuzzy logic integrated circuits both in PMOS and CMOS processes, a fuzzy memory device, fuzzy microprocessors in analog mode, a fuzzy logic computer, a fuzzy neuron chip and its application to hand-written character recognition, a chaos chip, and so on. He holds11 patents in U.S.A., 4 patents in Europe, 1 patent in Australia and 1 patent in Taiwan, and he has also applied for more than 90 patents in Japan. Dr. Yamakawa is a fellow of International Fuzzy Systems Association (IFSA) and Japan Society of Fuzzy Theory and Systems (SOFT), a senior member of IEEE, a member of the Institute of Electronics, Information and Communication Engineers (IEICE), the Society of Instrument and Control Engineers (SICE), the Japanese Neural Network Society and Japan Orthodontic Society. He is acting as a member of editorial board and a regional editor of 10 international professional journals. He contributed more than 80 international conferences as a member or the chairman of organizing/programming committee. He was used to organize the International Conference on Fuzzy Logic, Neural Nets and Soft Computing (IIZUKA Conference) every two years in Iizuka, Japan.
 He is currently acting as the director of the 21st Century Center of Excellence entitled "World of Brain Computing Interwoven out of Animals and Robots".

 

UP