Technische Universität Braunschweig, Informatik, Betriebssysteme und Rechnerverbund List of Online Documents ************************ Files ending in ".gz" are compressed using gzip (GNU zip). Use gunzip or gzip -d to uncompress them. For ftp, use binary transfer, for WWW use load to local disk option. The papers are postscript files (suffix .ps, ready to print. The bibliographies are BibTeX files (suffix .bib). o Neuro-Fuzzy Papers o Neuro-Fuzzy Bibliography o Uncertainty and Vagueness Papers o Network Management Papers o Load Balancing Papers o High Performance Networks and Multimedia Systems o Seminarausarbeitungen (in german) o Diplomarbeiten (in german) o Praktikumsunterlagen (in german) Neuro-Fuzzy Papers: ==================== o Eklund/Klawonn/Nauck: Distributing Errors in Neural Fuzzy Control. Paper of IIZUKA 92, Japan, 1992. (iizuka92.ps.gz) ABSTRACT: This paper describes a procedure to integrate techniques for the adaptation of membership functions in a linguistic variable based fuzzy control environment. o Nauck: NEFCON-I: Eine Simulationsumgebung fuer Neuronale Fuzzy Regler. Paper of the german GI-Workshop "Fuzzy-Systeme'93" in Braunschweig, 21.-22. Oct, 1993 (in German). For the english version see Nauck: Building Neural Fuzzy Controllers with NEFCON-I in: Kruse/Gebhardt/Klawonn: Fuzzy Systems in Computer Sience. Vieweg, Wiesbaden, 1994 (ISBN: 3-528-05456-5), pp.141-151. (bs-fuz93-german.ps.gz) ABSTRACT (the paper is in German): The NEFCON model presented in this paper has the advantage to be both interpretable as a neural network with fuzzy sets as its weights, and as a fuzzy controller. The learning algorithm based on this model does not result in structural changes, and does not affect the semantics of the underlying fuzzy controller. o Nauck: A Fuzzy Perceptron as a Generic Model for Neuro-Fuzzy Approaches. Paper of the 2nd German GI-Workshop "Fuzzy-Systeme'94 in Munich, Oct. '94" (paper in English). (fuzsys94.ps.gz) ABSTRACT: This paper presents a fuzzy perceptron as a generic model of multilayer fuzzy neural networks, or neural fuzzy systems, respectively. This model is suggested to ease the comparision of different neuro-fuzzy approaches that are known from the literature. A fuzzy perceptron is not a fuzzification of a common neural network architecture, and it is not our intention to enhance neural learning algorithms by fuzzy methods. The idea of the fuzzy perceptron is to provide an architecture that can be initialized with prior knowledge, and that can be trained using neural learning methods. The training is carried out in such a way that the learning result is interpretable in the form of linguistic fuzzy if-then rules. Next to the advantage of having a generic model to compare neuro-fuzzy models, the fuzzy perceptron can be specialized e.g. for data analysis and control tasks. o Nauck/Klawonn/Kruse: Fuzzy Sets, Fuzzy Controllers and Neural Networks. Presented at a workshop in Postsdam/Germany, 1992. (berlin.ps.gz) ABSTRACT: This paper gives a short introduction into Fuzzy Set Theory, presents an overview on fuzzy controllers, and discusses possible combinations between fuzzy controllers and neural networks. Fuzzy Sets suggested by L.A. Zadeh offer a possibility to formally describe linguistic expressions like tall, fast, medium, etc., and to operate on them. Fuzzy controllers use fuzzy sets to represent linguistic values of the input and output variables of a physical system, and describe their relations by fuzzy if-then rules. The idea of fuzzy control is to simulate a human expert who is able to control the system by translation of his or her linguistic inference rules into a control function. Artificial neural networks are highly parallel architectures consisting of simple processing elements which communicate through weighted connections. They are able to approximate functions or to solve certain tasks by learning from examples. Combinations of neural networks and fuzzy controllers can help to overcome problems in the design and tuning processes of fuzzy controllers. o Nauck/Klawonn/Kruse: Combining Neural Networks and Fuzzy Controllers. Presented at FLAI'93 in Linz/Austria, 1993. (flai93.ps.gz) ABSTRACT: Fuzzy controllers are designed to work with knowledge in the form of linguistic control rules. But the translation of these linguistic rules into the framework of fuzzy set theory depends on the choice of certain parameters, for which no formal method is known. The optimization of these parameters can be carried out by neural networks, which are designed to learn from training data, but which are in general not able to profit from structural knowledge. In this paper we discuss approaches which combine fuzzy controllers and neural networks, and present our own hybrid architecture where principles from fuzzy control theory and from neural networks are integrated into one system. o Nauck/Kruse: Interpreting changes in the fuzzy sets of a self adapting neural fuzzy controller. Paper of 2nd IFIS workshop, 1992. (ifis92.ps.gz) ABSTRACT: We describe a procedure for the adaptation of membership functions in a fuzzy control environment by using neural network learning principles. The changes in the fuzzy sets can be easily interpreted. By using a fuzzy error that is propagated back through the architecture of our fuzzy controller, we receive an unsupervised learning technique, where each rule tunes the membership functions of its antecedent and its consequence. o Nauck/Kruse: A neural fuzzy controller learning by fuzzy error propagation. Paper of NAFIPS '92, Puerto Vallarta, Mexico, 1992. (nafips92.ps.gz) ABSTRACT: In this paper we describe a procedure to integrate techniques for the adaptation of membership functions in a linguistic variable based fuzzy control environment by using neural network learning principles. This is an extension to our work in [ (iizuka92.ps.gz)]. We solve this problem by definining a fuzzy error that is propagated back through the architecture of our fuzzy controller. According to this fuzzy error and the strength of its antecedent each fuzzy rule determines its amount of error. Depending on the current state of the controlled system and the control action derived from the conclusion, each rule tunes the membership functions of its antecedent and its conclusion. By this we get an unsupervised learning technique that enables a fuzzy controller to adapt to a control task by knowing just about the global state and the fuzzy error. o Nauck/Kruse: A fuzzy neural network learning fuzzy control rules and membership functions by fuzzy error backpropagation. Paper of IEEE-ICNN in San Francisco, 1993. (icnn93.ps.gz) ABSTRACT: In this paper we present a new kind of neural network architecture designed for control tasks, which we call fuzzy neural network. The structure of the network can be interpreted in terms of a fuzzy controller. It has a three-layered architecture and uses fuzzy sets as its weights. The fuzzy error backpropagation algorithm, a special learning algorithm inspired by the standard BP-procedure for multilayer neural networks, is able to learn the fuzzy sets. The extended version that is presented here is also able to learn fuzzy-if-then rules by reducing the number of nodes in the hidden layer of the network. The network does not learn from examples, but by evaluating a special fuzzy error measure. o Nauck/Kruse: NEFCON-I: An X-Window Based Simulator for Neural Fuzzy Controllers. Paper of IEEE-ICNN 1994 at WCCI'94 in Orlando. (icnn94.ps.gz) ABSTRACT: In this paper we present NEFCON-I, a graphical simulation environment for building and training neural fuzzy controllers based on the NEFCON model [ (icnn93.ps.gz)]. NEFCON-I is an X-Window based software that allows a user to specify initial fuzzy sets, fuzzy rules and a rule based fuzzy error. The neural fuzzy controller is trained by a reinforcement learning procedure which is derived from the fuzzy error backpropagation algorithm for fuzzy perceptrons /CITE{nauck93d}. NEFCON-I communicates with an external process where a dynamical system is simulated. NEFCON-I is freely available on the internet. o Nauck/Kruse: Choosing Appropriate Neuro-Fuzzy Models. Paper of EUFIT'94 1994 in Aachen, Germany. (eufit94.ps.gz) ABSTRACT: To use fuzzy controllers for automization tasks appropriate fuzzy sets and fuzzy rules have to be defined. This can be difficult in some domains, and the resulting controller has to be tuned. Neuro-fuzzy models can help in this tuning process by adapting fuzzy sets and creating fuzzy rules. Combinations of neural networks and fuzzy controllers are suitable if there is only partial knowledge in the form of fuzzy sets and fuzzy rules, but training data is available. To be be able to choose an appropriate model one has to know the different approaches to neural fuzzy control. In this paper we present a classification of generic neural fuzzy controllers and give some hints when to choose a certain type of model. o Nauck/Kruse: NEFCLASS - A Neuro-Fuzzy Approach for the Classification of Data. Paper of Symposium on Applied Computing 1995 (SAC'95) in Nashville. (acm95.ps.gz) ABSTRACT: In this paper we present NEFCLASS, a neuro-fuzzy system for the classification of data. This approach is based on our generic model of a fuzzy perceptron which can be used to derive fuzzy neural networks or neural fuzzy systems for specific domains. The presented model derives fuzzy rules from data to classify patterns into a number of (crisp) classes. NEFCLASS uses a supervised learning algorithm based on fuzzy error backpropagation that is used in other derivations of the fuzzy perceptron. o Nauck: Beyond Neuro-Fuzzy: Perspectives and Directions. Paper of Third European Congress on Intelligent Techniques and Soft Computing (EUFIT'95) in Aachen. (eufit95.ps.gz) ABSTRACT: The interest in neuro-fuzzy systems has grown tremendously over the last few years. First approaches concentrated mainly on neuro-fuzzy controllers, whereas newer approaches can also be found in the domain of data analysis. After successful applications in Japan neuro-fuzzy concepts also find their way into the European industries, though mainly simple models, like FAMs, still prevail. This paper shortly reviews some modern neuro-fuzzy concepts. After this a generic neuro-fuzzy model is presented, that serves a foundation for specific derived neuro-fuzzy applications, this is shown with a model for neuro-fuzzy data analysis, which we see as an important perspective for the neuro-fuzzy domain. The paper concludes with some thoughts on further research directions that go beyond simple neuro-fuzzy control applications. o Nauck/Kruse/Stellmach: New Learning Algorithms for the Neuro-Fuzzy Environment NEFCON-I. Paper of the Third German GI-Workshop ``Fuzzy-Neuro-Systeme'95'', Darmstadt, Germany, November 15 - 17, 1995. (fuz95a.ps.gz) ABSTRACT: NEFCON-I is an X-Window based graphical simulation environment for neuro-fuzzy controllers, and it is freely available on the Internet. The NEFCON model is based on a generic fuzzy perceptron, and it is able to learn fuzzy sets and fuzzy rules by a reinforcement learning algorithm that uses a fuzzy error measure. The former version of NEFCON had some restrictions on the form of the membership functions of the conclusions, and an expensive rule learning procedure. The new version of the NEFCON model incorporates new learning algorithms for both the fuzzy sets, and the fuzzy rules, and it removes the restrictions on the conclusion fuzzy sets. o Klawonn/Nauck/Kruse: Generating Rules from Data by Fuzzy and Neuro-Fuzzy Methods. Paper of the Third German GI-Workshop ``Fuzzy-Neuro-Systeme'95'', Darmstadt, Germany, November 15 - 17, 1995. (fuz95b.ps.gz) ABSTRACT: In this paper we present an approach to neuro-fuzzy classification that is able to learn fuzzy sets and fuzzy rules from data. The fuzzy rules that are created by this approach can be very well interpreted, however, they do not classify as good as the rules derived by sophisticated fuzzy clustering algorithms. They on the other hand supply usually unsatisfying fuzzy sets what makes it hard to interpret the rules. Combining both approaches can eliminate these disadvantages. o Kruse/Nauck: Learning Methods for Fuzzy Systems. Paper of the Third German GI-Workshop ``Fuzzy-Neuro-Systeme'95'', Darmstadt, Germany, November 15 - 17, 1995. (fuz95c.ps.gz) ABSTRACT: In this paper we discuss one aspect on learning methods for fuzzy systems: the semantics of neuro-fuzzy systems. We show how a neuro-fuzzy system should be structured, so it can be easily interpreted, and how learning algorithms for these models can be constructed. Learning in neuro-fuzzy systems should always lead to interpretable fuzzy rules. As an example, we compare the fuzzy rules resulting from a fuzzy clustering procedure to the the learning results of a neuro-fuzzy system in the context of pattern classification. o Nauck/Kruse: Neuro--Fuzzy Classification with NEFCLASS. Paper of Symposium on Operations Research, Passau, 1995. (sor95.ps.gz) o Nauck/Nauck/Kruse: Generating Classification Rules with the Neuro-Fuzzy System NEFCLASS. Paper of the Biennial Conf. of the North American Fuzzy Information Processing Society (NAFIPS'96), Berkeley, June 19-22, 1996. (nafips96.ps.gz) ABSTRACT: Neuro--fuzzy systems have recently gained a lot of interest in research and application. In this paper we discuss NEFCLASS, a neuro--fuzzy approach for data analysis. We present new learning strategies to derive fuzzy classification rules from data, and show some results. o Nauck/Klawonn: Neuro-Fuzzy Classification Initialized by Fuzzy Clustering. Paper of Fourth European Congress on Intelligent Techniques and Soft Computing (EUFIT96), Aachen, Sep. 2-5, 1996. (eufit96.ps.gz) ABSTRACT: In this paper we discuss how a neuro-fuzzy classifier can be initialized by rules generated by fuzzy clustering. The neuro-fuzzy classifier NEFCLASS can learn fuzzy classification rules completely from data. The learning algorithm for fuzzy sets can be constrained in order to obtain interpretable classifiers. However, fuzzy clustering provides more sophisticated rule learning procedures. We show that the learning process of NEFCLASS produces better results, if it is initialized by fuzzy clustering Neuro-Fuzzy bibliography: ========================== o Nauck: A bibliography of articles, books, etc. of neuro-fuzzy combinations. It will be updated from time to time (last update on May 20, 1996). Format is BibTeX, ASCII. (fuzzy-nn.bib, 97KB) You can also download a ZIP archive (use pkunzip to uncompress) which is substantially smaller (fuzzy-nn.zip, 20KB) If you don't know what BibTeX is: The file is a BibTeX database ready to use in LaTeX documents. You can refer to it via the \cite{} command. Then you have to use the bibtex command after you completed the first latex run. You will then receive a file that can be used by LaTeX in the next two runs to fill your citations in your text with the correct references. For more information see e.g. the LaTeX book by Leslie Lamport. If you want to print the whole file, you can use the following latex document: \documentstyle{article} \begin{document} \nocite{*} \bibliography{fuzzy-nn} \bibliographystyle{alpha} \end{document} Put this in a file, say foo.tex and then use the commands: latex foo bibtex foo latex foo latex foo You will receive a dvi-file containing all references in alphabetical order. If you don't have latex, you can get the bibliography in printable form. Choose between dvi format fuzzy-nn.dvi.gz or PostScript format fuzzy-nn.ps.gz. Uncertainty and Vagueness Papers ================================= o Kruse/Nauck/Klawonn: Reasoning with Mass Distributions. Paper of Uncertainty in AI'91 conference, Los Angeles, 1991. (kruse-uai91.ps.gz) Network Management Papers: =========================== o Schönwälder/Langendörfer: Administration of large distributed UNIX LANs with BONES. Paper of SANS II, Arlington, Virginia, 1993. (bones.ps.gz) o Schönwälder/Langendörfer: INED - An Application Independent Network Editor. Paper of SANS II, Arlington, Virginia, 1993. (ined.ps.gz) o Schönwälder/Langendörfer: How To Keep Track of Your Network Configuration. Paper of LISA VII, Monterey, California, 1993. (discover.ps.gz) o Schönwälder/Langendörfer: Netzwerkmanagement - Beschreibung des Exponats auf der CeBIT '94. Informatik-Bericht 94-02, TU-Braunschweig, 1994 (in german). (cebit94.ps.gz) o Schönwälder/Langendörfer: Eine Netzwerkmanagement-Plattform basierend auf der Tool Command Language (Tcl). Paper of GUUG Workshop, Köln, 1995 (in german). (guugws-95.ps.gz) Slides of the talk are also available. (guugws-95.slides.ps.gz). o Schönwälder: Distributed Network Management - Approaches and Problems. Slides of a talk given at the University of Twente, April 1995. (twente-dnm.ps.gz). o Schönwälder/Langendörfer: Tcl Extensions for Network Management Applications. Paper of Tcl/Tk Workshop, Toronto, 1995. (tcltk-95.ps.gz) Slides of the talk are also available. (tcltk-95.slides.ps.gz). o Schönwälder/Langendörfer: Einbindung applikations-spezifischer Agenten in das SNMP Management. Paper of EMVA Workshop, Dortmund, 1995 (in german). (emva-95.ps.gz). o Schönwälder: Simple Network Management Protocol (SNMP): Past - Present - Future. Slides of a talk given at the GUUG Workshop, Köln, 1996. (guugws-96.slides.ps.gz). Load Balancing and Distributed Scheduling Papers: ================================================== o B. Schnor and H. Langendörfer and S. Petri: Einsatz neuronaler Netze zur Lastbalancierung in Workstationclustern. In Praxisorientierte Parallelverarbeitung, Ed. H. Langendörfer, Hanser, München, pages 154-165, October 1994 (in german). (yalb-pribs94.ps.gz) (56508 Bytes) o S. Petri and H. Langendörfer: Load Balancing and Fault Tolerance in Workstation Clusters -- Migrating Groups of Communicating Processes. In Operating Systems Review, volume 29, number 4, pages 25--36, October 1995. (pbeam-osr95.ps.gz) (52666 Bytes) o B. Schnor and S. Petri and R. Oleyniczak and H. Langendörfer: Scheduling of Parallel Applications on Heterogeneous Workstation Clusters. In Proceedings of the ISCA 9th International Conference on Parallel and Distributed Computing Systems, Ed. K. Yetongnon and S. Hariri, ISCA, Dijon, September 1996. (yalb-pdcs96.ps.gz) (56608 Bytes) High Performance Networks and Multimedia Systems: ================================================= o M. Zitterbart: Slides of the talk given at the Internet Kongreß, Karlsruhe, May 1996. (internkgr96.ps.gz) o A. Fieger, M. Zitterbart: Vortragsfolien: Kopplung von Funk- und Festnetzen, Auswirkungen auf der Transportschicht, OFDM Fachgespräch Braunschweig, September 1996. (ofdm96.ps.gz) Seminarausarbeitungen (in german): =================================== o Paralleles und Verteiltes Rechnen, Sommer 1994. o Paralleles und Verteiltes Rechnen - Fehlersuche und Fehlertoleranz in verteilten Systemen, Sommer 1995. o Paralleles und Verteiltes Rechnen - Lastausgleich in Verteilten Systemen, Sommer 1996. Diplomarbeiten: ================ o H.-J. Diekgerdes: NEFCON-I: Entwurf und Implementierung einer Entwicklungsumgebung fuer Neuronale Fuzzy-Regler. Diplomarbeit, TU Braunschweig, 1993 (in german). (diekgerdes.ps.gz) o S. Förster: Zu Kombinationen Neuronaler Netze und Fuzzy-Systemen. Diplomarbeit, TU Braunschweig, 1993 (in german). (foerster1.ps.gz) (foerster2.ps.gz) (foerster3.ps.gz) (foerster4.ps.gz) o S. Stille: Lastbalancierung in verteilten Systemen. Diplomarbeit, TU Braunschweig, 1993 (in german). (yalb-stille93.ps.gz) o H. Carlsson: Konfiguration von Lastbalancierungssystemen . Diplomarbeit, TU Braunschweig, 1994 (in german). (yalb-carlsson94.ps.gz) o C.-M. Grabb: Einsatz neuronaler Netze zur Lastermittlung in verteilten Systemen . Diplomarbeit, TU Braunschweig, 1995 (in german). (yalb-grabb95.ps.gz) o E. Körber: Werkzeuge zur Bewertung von Lastverteilungsverfahren . Studienarbeit, TU Braunschweig, 1995 (in german). (yalb-koerber95.ps.gz) o J. Steinborn: Globale konsistente Checkpoints für verteilte Anwendungen in Workstation Clustern. Diplomarbeit, TU Braunschweig, 1996 (in german). (pbeam-steinborn96.ps.gz) (180935 Bytes) o M. Bolz: MtS: Ein Minimales Thread-System für Ausbildungszwecke. Diplomarbeit, TU Braunschweig, 1994 (in german). (mts-bolz94.ps.gz) (189088 Bytes) o S. Petri: simuLan - Ein Werkzeug zur Simulation lokaler Netze. Diplomarbeit, TU Braunschweig, 1991 (in german). (simulan-petri91.ps.gz) (266378 Bytes) o R. Schmidt-Dannert: simuLan: Modellierung und Simulation lokaler Netzwerke. Diplomarbeit, TU Braunschweig, 1991 (in german). (simulan-schmida91.ps.gz) (403441 Bytes) Praktikumsunterlagen: ====================== o Petri/Schönwälder/Bolz/Strauß: Praktikum Verteilte Systeme. Unterlagen zum Praktikum vom Wintersemester 94/95. (Most probably of zero interest for people from other sites ;-) (pvs.ps.gz)