Manfred Glesner

Fast Perceptron Learning by Fuzzy Controlled Dynamic Adaptation of Network Parameters

Application of fuzzy control for obtaining better performance from conventional neural networks is a new area in the field of fuzzy-neural combined systems. Conventional backpropagation algorithm for example can be improved by changing network parameters, based on the empirical knowledge gained by the user. This manual adaptation is effectively replaced by a fuzzy controller that contains the a priori knowledge in form from membership functions and rules. The implemented modified backpropagation algorithm with a fuzzy controller for dynamic adaptation of network parameters is tested with a benchmark data set and two real world problems.

Defuzzification As Crisp Decision Under Fuzzy Constraints — New Aspects of Theory and Improved Defuzzification Algorithms

Although defuzzification is an essential functional part of all fuzzy systems, it is not firmly embedded in fuzzy theory yet.

CAPpartx: Computer Aided Prototyping Partitioning for Xilinx FPGAs, a Hierarchical Partitioning Tool for Rapid Prototyping

Rapid prototyping is a well accepted method in microelectronics. Early validation of an ASIC design is possible through emulation using FPGAs. Thus, specification errors can be eliminated and the overall development time and costs are reduced significantly. One of the main task in ASIC emulation is netlist partitioning. The approach we implemented is tailored to the architectural characteristics of application specific embedded controllers for mechatronic applications. It is based on a hierarchical partitioning strategy.