Computational Intelligence - Learning with Neural Methods on Structured Data

Publications B. Hammer

books - papers - talks - reports - varia

Books and book chapters:

• B.Hammer, M.Strickert, T.Villmann, Prototype based recognition of splice sites, to appear in U.Seiffert et al., Bioinformatics using computational intelligence

• B. Hammer, Perspectives on Learning Symbolic Data with Connectionistic Systems, R.Kühn, R.Menzel, W.Menzel, U.Ratsch, M.M.Richter, I.-O.Stamatescu, Adaptivity and Learning, 141-160, Springer, 2003.

• B. Hammer, Compositionality in Neural Systems, M. Arbib, Handbook of Brain Theory and Neural Networks, 2nd edition, 244-248, 2002.

• B. Hammer, Learning with Recurrent Neural Networks, Springer Lecture Notes in Control and Information Sciences 254, Springer-Verlag, 2000
  (This constitutes a considerably extended version of my PhD thesis)

• V. Sperschneider, B. Hammer, Theoretische Informatik - Eine problemorientierte Einführung, Springer-Verlag, 1996
  Postscript (.gz), Postscript (plain), pdf, and Errata

top

Journal articles and contributions to conference proceedings:

• B.Hammer, M.Strickert, T.Villmann, Relevance LVQ versus SVM, in: L.Rutkowski, J.Siekmann, R.Tadeusiewicz, L.A.Zadeh, Artificial Intelligence and Softcomputing, Springer Lecture Notes in Artificial Intelligence 3070, 592-597, 2004.

• M.Strickert, B.Hammer, Self-organizing context learning, in: M.Verleysen (ed.), European Symposium at Artificial Neural Networks'2004, D-side publications, 39-44, 2004.

• B.Hammer, B.J.Jain, Neural methods for non-standard data, in: M.Verleysen (ed.), European Symposium at Artificial Neural Networks'2004, D-side publications, 281-292, 2004.

• B.Hammer, M.Strickert, T.Villmann, Supervised Neural Gas with General Similarity Measure, to appear in Neural Processing Letters

• B.Hammer, A.Micheli, M.Strickert, A.Sperduti, A general framework for unsupervised processing of structured data, Neurocomputing 57, 3-35, 2004.

• T.Villmann, F.M.Schleif, B.Hammer, Supervised Neural Gas and Relevance Learning in Learning Vector Quantization, WSOM'03, 47-52, 2003.

• M. Strickert, B. Hammer, Neural Gas for Sequences, WSOM'03, 53-57, 2003.

• T. Bojer, B. Hammer, M. Strickert, and T. Villmann, Determining relevant input dimensions for the self-organizing map, in: L. Rutkowski and J. Kacprzyk (eds.), Neural Networks and Soft Computing (Proc. ICNNSC 2002), Physica-Verlag, 388-393, 2003.

• T. Villmann, E. Merenyi, B. Hammer, Neural maps in remote sensing image analysis, Neural Networks 16(3-4),389-403, 2003.

• M.Strickert, B.Hammer, Unsupervised recursive sequence processing, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2003, D-side publications, 27-32, 2003.

• K. Gersmann, B. Hammer, Improving iterative repair strategies for scheduling with the SVM, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2003, D-side publications, 235-240, 2003.

• T. Bojer, B. Hammer, C. Koers, Monitoring technical systems with prototype based clustering, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2003, D-side publications, 433-439, 2003.

• B. Hammer, T. Villmann, Mathematical aspects of neural networks, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2003, D-side publications, 59-72, 2003.

• P. Tino, B. Hammer, Architectural Bias in Recurrent Neural Networks - Fractal Analysis, Neural Computation 15(8), 1931-1957, 2003.

• B. DasGupta, B. Hammer, On approximate learning by multi-layered feedforward circuits, to appear in Theoretical Computer Science.

• B. Hammer, P. Tino, Recurrent neural networks with small weights implement definite memory machines, Neural Computation 15(8), 1897-1929, 2003.

• B. Hammer, T. Villmann, Generalized relevance learning vector quantization, Neural Networks 15, 1059-1068, 2002.

• B. Hammer, K. Gersmann, A note on the universal approximation capability of support vector machines, Neural Processing Letters 17, 43-53, 2003.

• P. Tino, B. Hammer, Architectural bias in recurrent neural networks - fractal analysis, in: J.R.Dorronsoro (Ed.), Artificial Neural Networks -- ICANN 2002, Springer, 1359-1364, 2002. (Best conference paper award)

• B. Hammer, A. Rechtien, M. Strickert, T. Villmann, Rule extraction from self-organizing maps, in: J.R.Dorronsoro (Ed.), Artificial Neural Networks -- ICANN 2002, Springer, 877-882, 2002.

• B. Hammer, M. Strickert, T. Villmann, Learning vector quantization for multimodal data, in: J.R.Dorronsoro (Ed.), Artificial Neural Networks -- ICANN 2002, Springer, 370-375, 2002.

• B. Hammer, J.J. Steil, Perspectives on learning with recurrent networks, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2002, D-side publications, 357-368, 2002

• B. Hammer, T. Villmann, Batch-RLVQ, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2002, D-side publications, 295-300, 2002

• B. Hammer, A. Micheli, A. Sperduti, A general framework for unsupervised processing of structured data, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2002, D-side publications, 389-394, 2002

• T. Villmann, B. Hammer, M. Strickert, Supervised neural gas for learning vector quantization, in: D.Polani, J.Kim, T.Martinetz (eds.), Fifth German Workshop on Artificial Life, IOS Press, 9-18, 2002

• B. Hammer, Recurrent networks for structured data - a unifying approach and its properties, Cognitive Systems Research 3(2), 145-165, 2002

• M. Strickert, T. Bojer, B. Hammer, Generalized relevance LVQ for time series, in: G.Dorffner, H.Bischof, K.Hornik (eds.), Artificial Neural Networks - ICANN'2001, Springer, 677-683, 2001

• B. Hammer, On the generalization ability of recurrent networks, in: G.Dorffner, H.Bischof, K.Hornik (eds.), Artificial Neural Networks - ICANN'2001, Springer, 731-736, 2001

• B. Hammer, T. Villmann, Estimating relevant input dimensions for self-organizing algorithms, in: N.Allison, H.Yin, L.Allinson, J.Slack (eds.), Advances in Self-Organizing Maps, Springer, 173-180, 2001

• B. Hammer, T. Villmann, Input pruning for neural gas architectures, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2001, D-facto publications, 283-288, 2001

• T. Bojer, B. Hammer, D. Schunk, K. Tluk von Toschanowitz, Relevance determination in learning vector quantization, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2001, D-facto publications, 271-276, 2001

• M. Vidyasagar, S. Balaji, B. Hammer, Closure properties of uniform convergence of empirical means and PAC learnability under a family of probability measures, System and Control Letters 42, 151-157, 2001

• B. DasGupta, B. Hammer, On approximate learning by multi-layered feedforward circuits, in: H. Arimura, S. Jain, A. Sharma (eds.), Algorithmic Learning Theory'2000, Springer, 264-278, 2000

• B. Hammer, Generalization ability of folding networks, IEEE Transactions on Knowledge and Data Engineering, 13(2): 196-206, 2001

• B. Hammer, Limitations of hybrid systems, in: M.Verleysen (ed.), European Symposium on Artificial Neural Networks'2000, D-facto publications, 213-218, 2000

• B. Hammer, On the approximation capability of recurrent neural networks, Neurocomputing, 31(1-4): 107-124, 2000

• B. Hammer, Approximation capabilities of folding networks, in: M. Verleysen (ed.), European Symposium on Artificial Neural Networks'99, D-facto publications, 33-38, 1999

• B. Hammer, On the learnability of recursive data, Mathematics of Control Signals and Systems, 12: 62-79, 1999

• B. Hammer, On the Approximation Capability of Recurrent Neural Networks (Best session presentation award), in: M. Heiss (ed.), International Symposium on Neural Computation'98, ICSC Academic Press, 512-518, 1998

• B. Hammer, Some complexity results for perceptron networks, in: L. Niklasson, M. Boden, T. Ziemke (eds.), International Conference on Artificial Neural Networks'98, Springer Verlag, 639-518, 1998 (erratum)

• B. Hammer, Training a sigmoidal network is difficult, in: M. Verleysen (ed.), European Symposium on Artificial Neural Networks'98, D-facto publications, 255-260, 1998

• B. Hammer, On the generalization of Elman networks, in: W. Gerstner, A. Germond, M. Hasler, J.-D. Nicaud (eds.), International Conference on Artificial Neural Networks'97, Springer Verlag, 409-414, 1997

• B. Hammer, V. Sperschneider Neural networks can approximate mappings on structured objects, in: P. P. Wang (ed.), International Conference on Computational Intelligence and Neural Networks'97, 211-414, 1997

top

Talks and poster presentations:

• B.Hammer, T.Bojer, E. Merenyi, F.Schleif, G.Singh Mrok, M.Strickert, T.Villmann, Data processing with neural networks, ISAS Dortmund (talk)

• B.Hammer, T.Bojer, M.Strickert, T.Villmann, A.Sperduti, A.Micheli, Self-organizing learning for non-standard data, Ruhr-Universität Bochum (talk)

• B.Hammer, B.J.Jain, Neural methods for non-standard data, ESANN'04 (talk)

• B.Hammer, T.Bojer, E.Merenyi, M.Strickert, T.Villmann, Datenverarbeitung mit Neuronalen Netzen, LLG (talk)

• B.Hammer et al., Lernende Software, Reihe IT meets Science, (talk, Folien)

• B.Hammer, Neuronale Netze für nicht-standard Daten, Universität Dortmund, (talk)

• B.Hammer, Neuronale Netze für strukturierte Daten, Habilitationsvortrag, (talk)

• B.Hammer, Ein Streifzug durch strukturverarbeitende Neuronale Netze, Universität Karlsruhe, (talk), 2003

• B.Hammer, Ant Colony Optimization, Habilitationsvortrag, (talk), 2003

• B.Hammer, Cascade Correlation für Strukturen, Habilitationsvortrag, (talk), 2003

• B.Hammer, A.Micheli, A.Sperduti, M.Strickert, Recursive Self-Organizing Networks, University of Birmingham, 2003 (talk)

• B.Hammer, T.Bojer, M.Strickert, T.Villmann, Relevance learning,
  - University of Birmingham, 2003 (talk)
  - RU Groningen, 2004 (talk)

• B.Hammer, Selbstorganisierende Neuronale Netze für Nicht-standard Daten, Universität Siegen (talk), 2003

• B.Hammer, T.Villmann, Tutorial: mathematical aspects of neural networks, ESANN'03, Bruges, Belgium, 2003 (talk)

• K.Gersmann, B.Hammer, Improving iterative repair strategies for scheduling with the SVM, ESANN'03, Bruges, Belgium, 2003 (poster)

• T.Bojer, B.Hammer C.Koers, Monitoring technical systems with prototype based clustering, ESANN'03, Bruges, Belgium, 2003 (poster)

• B.Hammer, P. Tino, Architectural bias in recurrent neural networks, (talk)

• B. Hammer, Neuronale Netze für strukturierte Daten, Universität des Saarlandes (talk)

• B. Hammer, M. Strickert, A. Micheli, A. Sperduti, Recursive neural networks for structured data, FB Informatik, Technische Universität Berlin (talk)

• B. Hammer, Selbstorganisierende Neuronale Verfahren für heterogene Daten, Technische Universität Clausthal (talk)

• B. Hammer, A.Rechtien, M. Strickert, Self-Organizing Neural Networks and Rule Extraction, Symposium on Logic and Creaticity, Cognitive Science, University of Osnabrück (poster,flyer)

• B. Hammer, Strukturverarbeitende Neuronale Netze, FB Mathematik, Universität Bielefeld, (talk)

• P. Tino, B. Hammer, Architectural Bias in Recurrent Neural Networks - Fractal analysis, ICANN'02, Madrid, Spain, 2002 (talk)

• B. Hammer, M. Strickert, T. Villmann, Learning Vector Quantization for Multimodal Data, ICANN'02, Madrid, Spain, 2002 (talk)

• B. Hammer, A. Rechtien, M. Strickert, T. Villmann, Rule Extraction from Self-Organizing Networks, ICANN'02, Madrid, Spain, 2002 (poster)

• T. Bojer, K. Gersmann, B. Hammer, A. Rechtien, M. Strickert, and external contributors, Perspektiven des Selbstorganisierenden Lernens, dies academicus, Universität Osnabrück, 2002 (sorry, only powerpoint, gzip-version, alte Version)

• B. Hammer, Self-Organizing Networks for Structural Data, 8th Annual German-American Forntiers of Science Meeting, Irvine, U.S.A., 2002 (poster a0, poster a1)

• B. Hammer, T. Villmann, Batch-RLVQ, ESANN'02, Bruges, Belgium, 2002 (talk)

• B. Hammer, J.J. Steil, Perspectives on learning with recurrent neural networks, ESANN'02, Bruges, Belgium, 2002 (talk)

• B.Hammer, A.Micheli, A.Sperduti, A proposal for a general framework for unsupervised learning in structured domains,
  - 3rd APoDS meeting, Department of Computer Science, University of Pisa, Italy, 2001 (talk)
  - Arbeitsgruppe Neuroinformatik, Universität Bielefeld, 2002

• B.Hammer, T.Bojer, A.Rechtien, M.Strickert, T.Villmann, Relevance determination in self-organizing neural networks, Department of Computer Science, University of Siena, Italy, 2001 (talk)

• B. Hammer, On the generalization ability of recurrent networks, ICANN'01, Vienna, Austria, 2001 (poster)

• B. Hammer, Processing structured data with recurrent neural networks, MPI für Mathematik in den Naturwissenschaften, Leipzig, 2001 (talk)

• B. Hammer, T. Villmann, Input pruning for neural gas architectures, ESANN'01, Bruges, Belgium, 2001 (talk)

• T. Bojer, B. Hammer, D. Schunk, K. Tluk von Toschanowitz, Relevance determination in learning vector quantization, ESANN'01, Bruges, Belgium, 2001 (talk)

• B. DasGupta, B. Hammer, On approximate learning by multi-layered feedforward circuits, ALT-2000, Sydney, Australia, 2000 (talk)

• B. Hammer, Perspectives on learning symbolic data with connectionistic systems, workshop at ZIF, Perspectives on Adaptivity and Learning, Bielefeld, 2000 (talk)

• B. Hammer, Approximation and generalization issues of recurrent networks dealing with structured data, ECAI-2000 workshop, Foundations of connectionistic-symbolic integration: representation, paradigms, and algorithms, Berlin, 2000 (talk)

• B. Hammer, Complexity results for perceptron networks, CO'2000, London, United Kingdom, 2000 (talk)

• B. Hammer, Neural networks classifying symbolic data, ICML-2000 workshop, Stanford, U.S.A., in L. de Raedt, S. Kramer (eds.): Proceedings of the ICML-2000 Workshop on Attribute-Value and Relational Learing: Crossing the Boundaries, 61-65, 2000 (talk)

• B. Hammer, Limitations of hybrid systems, ESANN'00, Bruges, Belgium, 2000 (poster, spotlight)

• B. Hammer, Complexity results for neural network training, CAIR, Bangalore, India, 2000 (talk)

• B. Hammer, Contributions to distribution dependent learnability, CAIR, Bangalore, India, 2000 (talk)

• B. Hammer, Folding networks - neural networks for structured data,
  - CAIR, Bangalore, India, 2000 (talk)
  - Department of Computer Science, Rutgers University, U.S.A., 1999 (talk)

• B. Hammer, Folding Netze - Neuronale Netze für strukturierte Daten,
  - Institut für Informatik, Universität Freiburg, 2000
  - Institut für Neuroinformatik, Ruhr-Universität Bochum, 1999
  - Institut für Logik, Komplexität und Deduktionssysteme, Universität Karlsruhe, 1999 (talk)
  - Arbeitsgruppe Neuroinformatik, Universität Bielefeld, 1999 (talk)
  

• B. Hammer, Approximation capabilities of folding networks, ESANN'99, Bruges, Belgium, 1999 (talk)

• B. Hammer, On the approximation capability of recurrent neural networks, NC'98, Vienna, Austria, 1998 (talk), (Best session presentation award)

• B. Hammer, Some complexity results for perceptron networks, ICANN'98, Skövde, Sweden, 1998 (poster)

• B. Hammer, Training a sigmoidal network is difficult, ESANN'98, Bruges, Belgium, 1998 (talk)

• B. Hammer, On the generalization of Elman networks, ICANN '97, Lausanne, Switzerland, 1997,

• B. Hammer, Lernen mit rekurrenten Netzen, Abteilung Neuroinformatik, Universität Ulm, 1997,

• B. Hammer, V. Sperschneider, Neural networks can approximate mappings on structured objects, ICCIN '97, Research Triangle Park, U.S.A., 1997

top

Technical reports:

• B. Hammer, M. Strickert, T. Villmann, On the generalization ability of GRLVQ networks, Osnabrücker Schriften zur Mathematik, Preprint, no. 249, 10/2003

• T. Villmann, B. Hammer, Metric adaptation and relevance learning in learning vector quantization, Osnabrücker Schriften zur Mathematik, Preprint, no. 247, 7/2003

• B. Hammer, A. Micheli, and A. Sperduti, A general framework for self-organizing structure processing neural networks, Technical Report TR-03-04, Dipartimento di Informatica, Universita di Pisa, 2003.

• B. Hammer, P. Tino, Neural networks with small weights implement finite memory machines, Osnabrücker Schriften zur Mathematik, Preprint, no. 241, 2/2002

• B. DasGupta, B. Hammer, Hardness of approximation of the loading problem for multi-layered feedforward networks, DIMACS Technical Report #99-60, DIMACS Center, Rutgers University, 1999

• B. Hammer, A NP-hardness Result for a Sigmoidal 3-Node Neural Network, Osnabrücker Schriften zur Mathematik, Preprint, no. 196, 11/1997

• B. Hammer, Learning recursive data is intractable, Osnabrücker Schriften zur Mathematik, Preprint, no. 194, 7/1997

• B. Hammer, On the Generalization Capability of Simple Recurrent Neural Networks, Osnabrücker Schriften zur Mathematik, Preprint, no. 190, 2/1997

• B. Hammer, Universal Approximation of Mappings on Structured Objects using the Folding Architecture, Osnabrücker Schriften zur Mathematik, Preprint, no. 183, 11/1996

top

Others:

• B.Hammer, Mathematical aspects of Neural Networks, 'Wrapper' around my Habilitationsschrift, Universität Osnabrück, 2003.

• B. Hammer, Learning with Recurrent Neural Networks, Dissertation, Universität Osnabrück, 1999

• B. Hammer, Die Beilinson-Spektralsequenz und Anwendungen, Diplomarbeit, Universität Osnabrück, 1995

• B. Hammer, Review of Neural Smithing (Russel D. Reed, Robert J. Marks II), Pattern analysis and Applications 4, 73-74, 2001.

• B. Hammer, Review of Eine Grundlegung der Average-Case Komplexitätstheorie (Ingrid Biehl), unix/mail 14(6):410, 1996

top

My CV.

B.Hammer