Author | Title | Year | Journal/Proceedings | Reftype | DOI/URL |
---|---|---|---|---|---|

van Zwieten, K.J., Duyvendak, W., Schmidt, K., Bex, G.J., Lippens, P., Gelan, J., Adriaensens, P. & Thywissen, C. | Paralysis of the intrinsic hand muscles after chronic neuropathy [BibTeX] |
2008 | Annual MS Research Days, pp. 25 | inproceedings | |

BibTeX:
@inproceedings{vZwi08a, author = {van Zwieten, Koos Jaap and Duyvendak, Wim and Schmidt, Klaus and Bex, Geert Jan and Lippens, Peter and Gelan, Jan and Adriaensens, Peter and Thywissen, Carlo}, title = {Paralysis of the intrinsic hand muscles after chronic neuropathy}, booktitle = {Annual MS Research Days}, year = {2008}, pages = {25} } |
|||||

van Zwieten, K.J., Lippens, P.L., Gelan, J., Adriaensens, P., Schmidt, K.P., Bex, G.J., Thywissen, C. & Duyvendak, W. | Forward and reverse kinematic modelling of normal finger motion, compared to finger motion in entrapment neuropathy [BibTeX] |
2008 | Knowledge for Growth | inproceedings | |

BibTeX:
@inproceedings{vZwi08, author = {K. J. van Zwieten and P. L. Lippens and J. Gelan and P. Adriaensens and K. P. Schmidt and G. J. Bex and C. Thywissen and W. Duyvendak}, title = {Forward and reverse kinematic modelling of normal finger motion, compared to finger motion in entrapment neuropathy}, booktitle = {Knowledge for Growth}, year = {2008} } |
|||||

van Zwieten, K.J., Schmidt, K., Bex, G., Lippens, P., Duyvendak, W. & Medaer, R. | Some factors contributing to the stabilisation of normal human fingers | 2009 | The musical body: gesture, representation and ergonomics in musical performance, pp. 27-28 | inproceedings | |

Abstract: The freely moving human hand, either in gesture or e.g. whilst preparing to strike the keys of a keyboard instrument, generally makes use of motions to be performed with stabilised finger positions. Any disturbed tonus of the muscles maintaining this stabilisation may produce an imbalance of agonists and antagonists, during the various trajectories that finger motions have to follow. This may eventually lead to focal dystonias - in hands of musicians and e.g. PC workers alike. The following overview will present some of the underlying mechanisms of normal finger stabilisation. Most analyses of finger interphalangeal coordination do not take into account the shifts of the different tendon fibre bundles within the so-called extensor assembly of the finger, which occur during interphalangeal motion. This finger extensor assembly consists of tendons from extrinsic and intrinsic finger extensor muscles. Its respective bundles are often depicted as single lines, although medial bundle and lateral bundles are flattened ribbon-like structures at proximal interphalangeal (P.I.P.) joint level. Beyond the extended joint these bundles maintain dorsal positions. Lateral bundles constitute the terminal extensor tendon of the distal interphalangeal (D.I.P.) joint. To demonstrate some of the subsequent positions of finger flexion, a mathematical simulation model of finger motion is used. In this kinematic model, tendons and tendon fibre bundles are supposed to be non-elastic and non-contractile, like ropes for instance. Simultaneous proximal interphalangeal flexion and distal interphalangeal flexion are correlated. Plotting of the successive angles of D.I.P. flexion against corresponding angles of P.I.P. flexion, in normal fingers, results in an S-curve. To analyse this S-curve, forward and reverse kinematic modelling of the extensor assembly of the finger may be applied. It is suggested that such curves may also add some prognostic value during diagnostics and rehabilitation of dystonias and other neuropathies in musicians suffering from hand problems. |
|||||

BibTeX:
@inproceedings{vZwi09, author = {Koos Jaap van Zwieten and K.P. Schmidt and G.J. Bex and P.L. Lippens and W. Duyvendak and R. Medaer}, title = {Some factors contributing to the stabilisation of normal human fingers}, booktitle = {The musical body: gesture, representation and ergonomics in musical performance}, year = {2009}, pages = {27--28} } |
|||||

Beenaerts, N., Bahir, M.M., Ng, P.K., Yeo, D.C.J., Bex, G.J., Pethyagoda, R. & Artois, T. | Phylogenetic diversity of Sri Lankan freshwater crabs and its implications for conservation | 2010 | Molecular Ecology Vol. 19(1), pp. 183-196 |
article | DOI |

Abstract: As part of a Global Biodiversity Hotspot, the conservation of Sri Lanka's endemic biodiversity warrants special attention. With 51 species (50 of them endemic) occurring in the island, the biodiversity of freshwater crabs is unusually high for such a small area (65 600 km2). Freshwater crabs have successfully colonized most moist habitats and all climatic and elevational zones in Sri Lanka. We assessed the biodiversity of these crabs in relation to the different elevational zones (lowland, upland and highland) based on both species richness and phylogenetic diversity. Three different lineages appear to have radiated simultaneously, each within a specific elevational zone, with little interchange thereafter. The lowland and upland zones show a higher species richness than the highland zone while – unexpectedly – phylogenetic diversity is highest in the lowland zone, illustrating the importance of considering both these measures in conservation planning. The diversity indices for the species in the various IUCN Red List categories in each of the three zones suggest that risk of extinction may be related to elevational zone. Our results also show that overall more than 50% of Sri Lanka's freshwater crab species (including several as yet undescribed ones), or approximately 72 million years of evolutionary history, are threatened with extinction. |
|||||

BibTeX:
@article{Been10, author = {Natalie Beenaerts and Mohomed M. Bahir and Peter K.L. Ng and Darren C. J. Yeo and Geert Jan Bex and Rohan Pethyagoda and Tom Artois}, title = {Phylogenetic diversity of Sri Lankan freshwater crabs and its implications for conservation}, journal = {Molecular Ecology}, year = {2010}, volume = {19}, number = {1}, pages = {183--196}, note = {accepted for Molecular Ecology}, doi = {http://dx.doi.org/10.1111/j.1365-294X.2009.04439.x} } |
|||||

Bex, G.J. | Discovering structure in semi-structured data [BibTeX] |
2008 | School: Hasselt University |
phdthesis | |

BibTeX:
@phdthesis{Bex08b, author = {Geert Jan Bex}, title = {Discovering structure in semi-structured data}, school = {Hasselt University}, year = {2008} } |
|||||

Bex, G.J. | Website rendering: bridging the gap between static and dynamic information [BibTeX] |
1997 | DECUS BELUX, Mol, Belgium | inproceedings | |

BibTeX:
@inproceedings{Bex97a, author = {Geert Jan Bex}, title = {Website rendering: bridging the gap between static and dynamic information}, booktitle = {DECUS BELUX, Mol, Belgium}, year = {1997} } |
|||||

Bex, G.J. | Beyond the web hype: using WWW for education and research [BibTeX] |
1996 | DECUS BELUX, La Roche-en-Ardennes, Belgium | inproceedings | |

BibTeX:
@inproceedings{Bex96a, author = {Geert Jan Bex}, title = {Beyond the web hype: using WWW for education and research}, booktitle = {DECUS BELUX, La Roche-en-Ardennes, Belgium}, year = {1996} } |
|||||

Bex, G.J. | Tuning the transfer function: the reversed wedge and beyond [BibTeX] |
1996 | School: Limburgs Universitair Centrum |
phdthesis | |

BibTeX:
@phdthesis{Bex96b, author = {Geert Jan Bex}, title = {Tuning the transfer function: the reversed wedge and beyond}, school = {Limburgs Universitair Centrum}, year = {1996} } |
|||||

Bex, G.J. | Generalization with neural networks [BibTeX] |
1995 | Physicalia Magazine Vol. 17(1), pp. 27-44 |
article | |

BibTeX:
@article{Bex95b, author = {Geert Jan Bex}, title = {Generalization with neural networks}, journal = {Physicalia Magazine}, year = {1995}, volume = {17}, number = {1}, pages = {27--44} } |
|||||

Bex, G.J. & Bonckaert, P. | Java: brewing for education [BibTeX] |
1997 | DECUS BELUX, Mol, Belgium | inproceedings | |

BibTeX:
@inproceedings{Bex97b, author = {Geert Jan Bex and Patrick Bonckaert}, title = {Java: brewing for education}, booktitle = {DECUS BELUX, Mol, Belgium}, year = {1997} } |
|||||

Bex, G.J., Gelade, W., Martens, W. & Neven, F. | Simplifying XML schema: effortless handling of nondeterministic regular expressions | 2009 | #SIGMOD#, pp. 731-744 | inproceedings | DOI |

Abstract: Whether beloved or despised, XML Schema is momentarily the only industrially accepted schema language for XML and is unlikely to become obsolete any time soon. Nevertheless, many nontransparent restrictions unnecessarily complicate the design of XSDs. For instance, complex content models in XML Schema are constrained by the infamous unique particle attribution (UPA) constraint. In formal language theoretic terms, this constraint restricts content models to deterministic regular expressions. As the latter constitute a semantic notion and no simple corresponding syntactical characterization is known, it is very difficult for non-expert users to understand exactly when and why content models do or do not violate UPA. In the present paper, we therefore investigate solutions to relieve users from the burden of UPA by automatically transforming nondeterministic expressions into concise deterministic ones defining the same language or constituting good approximations. The presented techniques facilitate XSD construction by reducing the design task at hand more towards the complexity of the modeling task. In addition, our algorithms can serve as a plug-in for any model management tool which supports export to XML Schema format. |
|||||

BibTeX:
@inproceedings{Bex09, author = {Geert Jan Bex and Wouter Gelade and Wim Martens and Frank Neven}, title = {Simplifying XML schema: effortless handling of nondeterministic regular expressions}, booktitle = {#SIGMOD#}, year = {2009}, pages = {731--744}, doi = {http://doi.acm.org/10.1145/1559845.1559922} } |
|||||

Bex, G.J., Gelade, W., Neven, F. & Vansummeren, S. | Learning deterministic regular expressions for the inference of schemas from XML data | 2010 | TWEB Vol. 4(4) |
article | DOI |

Abstract: Inferring an appropriate DTD or XML Schema Definition (XSD) for a given collection of XML documents essentially reduces to learning deterministic regular expressions from sets of positive example words. Unfortunately, there is no algorithm capable of learning the complete class of deterministic regular expressions from positive examples only, as we will show. The regular expressions occurring in practical DTDs and XSDs, however, are such that every alphabet symbol occurs only a small number of times. As such, in practice it suffices to learn the subclass of deterministic regular expressions in which each alphabet symbol occurs at most k times, for some small k. We refer to such expressions as k-occurrence regular expressions (k-OREs for short). Motivated by this observation, we provide a probabilistic algorithm that learns k-OREs for increasing values of k, and selects the deterministic one that best describes the sample based on a Minimum Description Length argument. The effectiveness of the method is empirically validated both on real world and synthetic data. Furthermore, the method is shown to be conservative over the simpler classes of expressions considered in previous work. |
|||||

BibTeX:
@article{Bex10a, author = {Geert Jan Bex and Wouter Gelade and Frank Neven and Stijn Vansummeren}, title = {Learning deterministic regular expressions for the inference of schemas from XML data}, journal = {TWEB}, year = {2010}, volume = {4}, number = {4}, doi = {http://doi.acm.org/10.1145/1841909.1841911} } |
|||||

Bex, G.J., Gelade, W., Neven, F. & Vansummeren, S. | Learning deterministic regular expressions for the inference of schemas from XML data | 2008 | #WWW#, pp. 825-834 | inproceedings | |

Abstract: Inferring an appropriate DTD or XML Schema Denition (XSD) for a given collection of XML documents essentially reduces to learning deterministic regular expressions from sets of positive example words. Unfortunately, there is no algorithm capable of learning the complete class of deterministic regular expressions from positive examples only, as we will show. The regular expressions occurring in practical DTDs and XSDs, however, are such that every alphabet symbol occurs only a small number of times. As such, in practice it suces to learn the subclass of regular expressions in which each alphabet symbol occurs at most k times, for some small k. We refer to such expressions as k-occurrence regular expressions (k-OREs for short). Motivated by this observation, we provide a probabilistic algorithm that learns k-OREs for increasing values of k, and selects the one that best describes the sample based on a Minimum Description Length argument. The effectiveness of the method is empirically validated both on real world and synthetic data. Furthermore, the method is shown to be conservative over the simpler classes of expressions considered in previous work. |
|||||

BibTeX:
@inproceedings{Bex08, author = {Geert Jan Bex and Wouter Gelade and Frank Neven and Stijn Vansummeren}, title = {Learning deterministic regular expressions for the inference of schemas from XML data}, booktitle = {#WWW#}, year = {2008}, pages = {825--834} } |
|||||

Bex, G.J., Maneth, S. & Neven, F. | A formal model for an expressive fragment of XSLT [BibTeX] |
2002 | Information Systems Vol. 27(1), pp. 21-39 |
article | DOI |

BibTeX:
@article{Bex02, author = {Geert Jan Bex and Sebastian Maneth and Frank Neven}, title = {A formal model for an expressive fragment of XSLT}, journal = {Information Systems}, year = {2002}, volume = {27}, number = {1}, pages = {21--39}, doi = {http://dx.doi.org/10.1016/S0306-4379(01)00033-3} } |
|||||

Bex, G.J., Maneth, S. & Neven, F. | A formal model for an expressive fragment of XSLT | 2000 | Vol. 1861Computational Logic -- CL2000, pp. 1137-1151 |
inproceedings | DOI URL |

Abstract: The aim of this paper is two-fold. First, we want to show that the recent extension of XSL with variables and passing of data values between template rules has increased its expressiveness beyond that of most other current XML query languages. Second, in an attempt to increase the understanding of this already wide-spread but not so transparent language, we provide an essential and powerful fragment with a formal syntax and a precise semantics. |
|||||

BibTeX:
@inproceedings{Bex00, author = {Geert Jan Bex and Sebastian Maneth and Frank Neven}, title = {A formal model for an expressive fragment of XSLT}, booktitle = {Computational Logic -- CL2000}, publisher = {Springer Verlag}, year = {2000}, volume = {1861}, pages = {1137--1151}, url = {http://link.springer.de/link/service/series/0558/bibs/1861/18611137.htm}, doi = {http://dx.doi.org/10.1007/3-540-44957-4_76} } |
|||||

Bex, G.J., Martens, W., Neven, F. & Schwentick, T. | Expressiveness of XSDs: from practice to theory, there and back again | 2005 | #WWW#, pp. 712-721 | inproceedings | DOI |

Abstract: On an abstract level, XML Schema increases the limited expressive power of Document Type Definitions (DTDs) by extending them with a recursive typing mechanism. However, an investigation of the XML Schema Definitions (XSDs) occurring in practice reveals that the vast majority of them are structurally equivalent to DTDs. This might be due to the complexity of the XML Schema specification and the difficulty to understand the effect of constraints on typing and validation of schemas. To shed some light on the actual expressive power of XSDs this paper studies the impact of the Element Declarations Consistent (EDC) and the Unique Particle Attribution (UPA) rule. An equivalent formalism based on contextual patterns rather than on recursive types is proposed which might serve as a light-weight front end for XML Schema. Finally, the effect of EDC and UPA on the way XML documents can be typed is discussed. It is argued that a cleaner, more robust, stronger but equally efficient class is obtained by replacing EDC and UPA with the notion of 1-pass preorder typing: schemas that allow to determine the type of an element of a streaming document when its opening tag is met. This notion can be defined in terms of restrained competition regular expressions and there is again an equivalent syntactical formalism based on contextual patterns. |
|||||

BibTeX:
@inproceedings{Bex05, author = {Geert Jan Bex and Wim Martens and Frank Neven and Thomas Schwentick}, title = {Expressiveness of XSDs: from practice to theory, there and back again}, booktitle = {#WWW#}, year = {2005}, pages = {712--721}, doi = {http://dx.doi.org/10.1145/1060745.1060848} } |
|||||

Bex, G.J., Neven, F., Schwentick, T. & Tuyls, K. | Inference of concise DTDs from XML data | 2006 | Proceedings of Conference on Very Large Databases (VLDB), pp. 115-126 | inproceedings | URL |

Abstract: We consider the problem to infer a concise Document Type Definition (DTD) for a given set of XML-documents, a problem which basically reduces to learning of concise regular expressions from positive example strings. We identify two such classes: single occurrence regular expressions (SOREs) and chain regular expressions (CHAREs). Both classes capture the far majority of the regular expressions occurring in practical DTDs and are succinct by definition. We present the algorithm re (infer DTD) that learns SOREs from strings by first inferring an automaton by known techniques and then translating that automaton to a corresponding SORE, possibly by repairing the automaton when no equivalent SORE can be found. In the process, we introduce a novelautomaton to regular expression rewrite technique which is of independent interest. We show that re outperforms existing systems in accuracy, conciseness and speed. In a scenariowhere only a very small amount of XML data is available, for instance when generated by Web service requests or by answers to queries, re produces regular expressions which are toospecific. Therefore, we introduce a novel learning algorithm CRX that directly infers CHAREs (which form a subclass of SOREs) without going through an automaton representation. We showthat CRX performs very well within its target class on very small data sets. Finally, we discuss incremental computation, noise, numerical predicates, and the generation of XML Schemas. |
|||||

BibTeX:
@inproceedings{Bex06, author = {Geert Jan Bex and Frank Neven and Thomas Schwentick and Karl Tuyls}, title = {Inference of concise DTDs from XML data}, booktitle = {Proceedings of Conference on Very Large Databases (VLDB)}, year = {2006}, pages = {115--126}, url = {http://www.vldb.org/conf/2006/p115-bex.pdf} } |
|||||

Bex, G.J., Neven, F., Schwentick, T. & Tuyls, K. | Inference of concise DTDs from XML data [BibTeX] |
2006 | BNAIC, pp. 357-358 | inproceedings | |

BibTeX:
@inproceedings{Bex06b, author = {Geert Jan Bex and Frank Neven and Thomas Schwentick and Karl Tuyls}, title = {Inference of concise DTDs from XML data}, booktitle = {BNAIC}, year = {2006}, pages = {357--358}, note = {Compressed contribution, see Bex06} } |
|||||

Bex, G.J., Neven, F., Schwentick, T. & Vansummeren, S. | Inference of concise regular expressions and DTDs | 2010 | ACM Transactions on Database Systems Vol. 35(2) |
article | DOI |

Abstract: We consider the problem of inferring a concise Document Type Definition (DTD) for a given set of XML-documents, a problem that basically reduces to learning concise regular expressions from positive examples strings. We identify two classes of concise regular expressions, the single occurrence regular expressions (SOREs) and the chain regular expressions (CHAREs)|that capture the far majority of expressions used in practical DTDs. For the inference of SOREs we present several algorithms that on a given set of example strings rst infer an automaton using known techniques and then translate that automaton to a corresponding SORE, possibly repairing the automaton when no equivalent SORE can be found. In the process, we introduce a novel automaton to regular expression rewrite technique which is of independent interest. We show that our algorithms outperform existing systems in accuracy, conciseness and speed. When only a very small amount of XML data is available, however, (for instance when the data is generated by Web service requests or by answers to queries), these algorithms produce regular expressions that are too specic. Therefore, we introduce a novel learning algorithm crx that directly infers CHAREs (which form a subclass of SOREs) without going through an automaton representation. We show that crx performs very well within its target class on very small data sets. |
|||||

BibTeX:
@article{Bex10, author = {Geert Jan Bex and Frank Neven and Thomas Schwentick and Stijn Vansummeren}, title = {Inference of concise regular expressions and DTDs}, journal = {ACM Transactions on Database Systems}, year = {2010}, volume = {35}, number = {2}, note = {accepted for publication in ACM Transactions on Database Systems}, doi = {http://dx.doi.org/10.1145/1735886.1735890} } |
|||||

Bex, G.J., Neven, F. & Van den Bussche, J. | DTDs versus XML Schema: a practical study | 2004 | Proceedings of WebDB, pp. 79-84 | inproceedings | DOI |

Abstract: Among the various proposals answering the shortcomings of Document Type Definitions (DTDs), XML Schema is the most widely used. Although DTDs and XML Schema Defintions (XSDs) di er syntactically, they are still quite related on an abstract level. Indeed, freed from all syntactic sugar, XML Schemas can be seen as an extension of DTDs with a restricted form of specialization. In the present paper, we inspect a number of DTDs and XSDs harvested from the web and try to answer the following questions: (1) which of the extra features/expressiveness of XML Schema not allowed by DTDs are e ectively used in practice; and, (2) how sophisticated are the structural properties (i.e. the nature of regular expressions) of the two formalisms. It turns out that at present real-world XSDs only sparingly use the new features introduced by XML Schema: on a structural level the vast majority of them can already be defined by DTDs. Further, we introduce a class of simple regular expressions and obtain that a surprisingly high fraction of the content models belong to this class. The latter result sheds light on the justification of simplifying assumptions that sometimes have to be made in XML research. |
|||||

BibTeX:
@inproceedings{Bex04, author = {Geert Jan Bex and Frank Neven and Jan Van den Bussche}, title = {DTDs versus XML Schema: a practical study}, booktitle = {Proceedings of WebDB}, year = {2004}, pages = {79--84}, doi = {http://dx.doi.org/10.1145/1017074.1017095} } |
|||||

Bex, G.J., Neven, F. & Vansummeren, S. | SchemaScope: a system for inferring and cleaning XML schemas [BibTeX] |
2008 | Proceedings of SIGMOD Conference, pp. 1259-1262 | inproceedings | |

BibTeX:
@inproceedings{Bex08a, author = {Geert Jan Bex and Frank Neven and Stijn Vansummeren}, title = {SchemaScope: a system for inferring and cleaning XML schemas}, booktitle = {Proceedings of SIGMOD Conference}, year = {2008}, pages = {1259--1262} } |
|||||

Bex, G.J., Neven, F. & Vansummeren, S. | Inferring XML Schema Definitions from XML data | 2007 | Proceedings of International Conference on Very Large Databases (VLDB), pp. 998-1009 | inproceedings | URL |

Abstract: Although the presence of a schema enables many optimizations for operations on XML documents, recent studies have shown that many XML documents in practice either do not refer to a schema, or refer to a syntactically incorrect one. It is therefore of utmost importance to provide tools and techniques that can automatically generate schemas from sets of sample documents. While previous work in this area has mostly focused on the inference of Document Type Definitions (DTDs for short), we will consider the inference of XML Schema Definitions (XSDs for short) ? the increasingly popular schema formalism that is turning DTDs obsolete. In contrast to DTDs where the content model of an element depends only on the element?s name, the content model in an XSD can also depend on the context in which the element is used. Hence, while the inference of DTDs basically reduces to the inference of regular expressions from sets of sample strings, the inference of XSDs also entails identifying from a corpus of sample documents the contexts in which elements bear different content models. Since a seminal result by Gold implies that no inference algorithm can learn the complete class of XSDs from positive examples only, we focus on a class of XSDs that captures most XSDs occurring in practice. For this class, we provide a theoretically complete algorithm that always infers the correct XSD when a sufficiently large corpus of XML documents is available. In addition, we present a variant of this algorithm that works well on real-world (and therefore incomplete) data sets. |
|||||

BibTeX:
@inproceedings{Bex07, author = {Geert Jan Bex and Frank Neven and Stijn Vansummeren}, title = {Inferring XML Schema Definitions from XML data}, booktitle = {Proceedings of International Conference on Very Large Databases (VLDB)}, year = {2007}, pages = {998--1009}, url = {http://www.vldb.org/conf/2007/papers/research/p998-bex.pdf} } |
|||||

Bex, G.J. & Serneels, R. | Non-monotonic transfer functions as an alternative to hidden layers [BibTeX] |
1994 | Fuzzy Logic and Intelligent Technologies in Nuclear Science | inproceedings | |

BibTeX:
@inproceedings{Bex94a, author = {Geert Jan Bex and Roger Serneels}, title = {Non-monotonic transfer functions as an alternative to hidden layers}, booktitle = {Fuzzy Logic and Intelligent Technologies in Nuclear Science}, publisher = {World Scientific}, year = {1994} } |
|||||

Bex, G.J. & Serneels, R. | Solving XOR without hidden layers [BibTeX] |
1994 | Belgian neural network contact group proceedings 1994 | inproceedings | |

BibTeX:
@inproceedings{Bex94b, author = {Geert Jan Bex and Roger Serneels}, title = {Solving XOR without hidden layers}, booktitle = {Belgian neural network contact group proceedings 1994}, publisher = {Université Catholique de Louvain}, year = {1994} } |
|||||

Bex, G.J. & Serneels, R. | Storage capacity of the reversed wedge perceptron with binary connections [BibTeX] |
1994 | ESANN | inproceedings | |

BibTeX:
@inproceedings{Bex94c, author = {Geert Jan Bex and Rorger Serneels}, title = {Storage capacity of the reversed wedge perceptron with binary connections}, booktitle = {ESANN}, publisher = {D Facto Publications}, year = {1994} } |
|||||

Bex, G.J., Serneels, R. & Van den Broeck, C. | Storage capacity and generalization error for the reversed wedge Ising perceptron | 1995 | Phys. Rev. E Vol. 51(6), pp. 6309-6312 |
article | DOI |

Abstract: Using the replica formalism, we evaluate the storage capacity and the generalization error of a perceptron with a reversed-wedge transfer function and binary synaptic weights. Remarkably, both the storage capacity and the generalization threshold saturate the information theoretic (respectively upper and lower) bound ?=1 for a specific choice of the width of the reverse wedge, suggesting that this perceptron may be an interesting building block for neural networks. |
|||||

BibTeX:
@article{Bex95a, author = {Geert Jan Bex and Roger Serneels and Chris Van den Broeck}, title = {Storage capacity and generalization error for the reversed wedge Ising perceptron}, journal = {Phys. Rev. E}, year = {1995}, volume = {51}, number = {6}, pages = {6309-6312}, doi = {http://dx.doi.org/10.1103/PhysRevE.51.6309} } |
|||||

Bex, G.J. & Van den Broeck, C. | Domain size of the Gardner volume for the Ising reversed wedge perceptron | 1997 | Phys. Rev. E Vol. 56(1), pp. 870-876 |
article | DOI |

Abstract: We investigate the subdivision of the Gardner volume into its internal representations for the Ising reversed wedge perceptron. The results are surprisingly complicated, displaying transitions between several qualitatively different regimes and involving replica symmetry breaking. These features remain completely hidden in the calculation of the total Gardner volume. |
|||||

BibTeX:
@article{Bex97, author = {Geert Jan Bex and Chris Van den Broeck}, title = {Domain size of the Gardner volume for the Ising reversed wedge perceptron}, journal = {Phys. Rev. E}, year = {1997}, volume = {56}, number = {1}, pages = {870--876}, doi = {http://dx.doi.org/10.1103/PhysRevE.56.870} } |
|||||

Callebaut, D.K. & Bex, G.J. | Perturbations of stationary chasma layers [BibTeX] |
1989 | Vol. 2XIX ICPIG, Beograd, Yougoslavia, pp. 274-275 |
inproceedings | |

BibTeX:
@inproceedings{Call89a, author = {Dirk K. Callebaut and Geert Jan Bex}, title = {Perturbations of stationary chasma layers}, booktitle = {XIX ICPIG, Beograd, Yougoslavia}, year = {1989}, volume = {2}, pages = {274--275} } |
|||||

Callebaut, D.K. & Bex, G.J. | Simple chasma equilibria and stability [BibTeX] |
1989 | Workshop V on (nonlinear) stability, Phys. Dept. UIA, Belgium | inproceedings | |

BibTeX:
@inproceedings{Call89b, author = {Dirk K. Callebaut and Geert Jan Bex}, title = {Simple chasma equilibria and stability}, booktitle = {Workshop V on (nonlinear) stability, Phys. Dept. UIA, Belgium}, year = {1989} } |
|||||

Hollanders, G., Bex, G.J., Gyssens, M., Tuyls, K. & Westra, R. | Learning sparse networks from poor data [BibTeX] |
2007 | BeNeLearn, pp. 30-36 | inproceedings | |

BibTeX:
@inproceedings{Holl07b, author = {Goele Hollanders and Geert Jan Bex and Marc Gyssens and Karl Tuyls and Ronald Westra}, title = {Learning sparse networks from poor data}, booktitle = {BeNeLearn}, year = {2007}, pages = {30--36} } |
|||||

Hollanders, G., Bex, G.J., Gyssens, M., Westra, R.L. & Tuyls, K. | On phase transitions in learning sparse networks | 2007 | Proceedings of ECML, pp. 591-599 | inproceedings | DOI |

Abstract: In this paper we study the identification of sparse interaction networks as a machine learning problem. Sparsity mean that we are provided with a small data set and a high number of unknown components of the system, most of which are zero. Under these circumstances, a model needs to be learned that fits the underlying system, capable of generalization. This corresponds to the student-teacher setting in machine learning. In the first part of this paper we introduce a learning algorithm, based on L 1-minimization, to identify interaction networks from poor data and analyze its dynamics with respect to phase transitions. The efficiency of the algorithm is measured by the generalization error, which represents the probability that the student is a good fit to the teacher. In the second part of this paper we show that from a system with a specific system size value the generalization error of other system sizes can be estimated. A comparison with a set of simulation experiments show a very good fit. |
|||||

BibTeX:
@inproceedings{Holl07, author = {Goele Hollanders and Geert Jan Bex and Mark Gyssens and Ronald L. Westra and Karl Tuyls}, title = {On phase transitions in learning sparse networks}, booktitle = {Proceedings of ECML}, year = {2007}, pages = {591--599}, doi = {http://dx.doi.org/10.1007/978-3-540-74958-5_57} } |
|||||

Hollanders, G., Bex, G.J., Gyssens, M., Westra, R.L. & Tuyls, K. | On phase transitions in learning sparse networks [BibTeX] |
2007 | BNAIC, pp. 359-360 | inproceedings | |

BibTeX:
@inproceedings{Holl07a, author = {Goele Hollanders and Geert Jan Bex and Marc Gyssens and Ronald L. Westra and Karl Tuyls}, title = {On phase transitions in learning sparse networks}, booktitle = {BNAIC}, year = {2007}, pages = {359--360} } |
|||||

Knuyt, G., Stulens, H., De Ceuninck, W., Bex, G.J. & Stals, L.M. | A simple method of calculating an energy spectrum from isothermal measurements using Fourier techniques | 1992 | Phil. Mag. B Vol. 65(5), pp. 1053-1065 |
article | DOI |

Abstract: A new method is presented to derive the spectrum of activation energies from isothermal measurements. When the integral describing the experimental data is written in a suitable form, a Fourier analysis of the relevant functions leads to an easy solution of the problem. The method turns out to be a very rapid and efficient one, in which the number of data points processed in the analysis can be made very large. The energy resolution of the calculated spectra is not limited by the method of calculation, but only by the finite number of data points and by the experimental errors on them. |
|||||

BibTeX:
@article{Knuy92, author = {Gilbert Knuyt and Herwig Stulens and Ward De Ceuninck and Geert Jan Bex and Lambert M. Stals}, title = {A simple method of calculating an energy spectrum from isothermal measurements using Fourier techniques}, journal = {Phil. Mag. B}, year = {1992}, volume = {65}, number = {5}, pages = {1053-1065}, doi = {http://dx.doi.org/10.1080/13642819208217920} } |
|||||

Martens, W., Neven, F., Schwentick, T. & Bex, G.J. | Expressiveness and complexity of XML Schema | 2006 | ACM Transactions on Database Systems Vol. 31(3), pp. 770 - 813 |
article | DOI |

Abstract: The common abstraction of XML Schema by unranked regular tree languages is not entirely accurate. To shed some light on the actual expressive power of XML Schema, intuitive semantical characterizations of the Element Declarations Consistent (EDC) rule are provided. In particular, it is obtained that schemas satisfying EDC can only reason about regular properties of ancestors of nodes. Hence, with respect to expressive power, XML Schema is closer to DTDs than to tree automata. These theoretical results are complemented with an investigation of the XML Schema Definitions (XSDs) occurring in practice, revealing that the extra expressiveness of XSDs over DTDs is only used to a very limited extent. As this might be due to the complexity of the XML Schema specification and the difficulty of understanding the effect of constraints on typing and validation of schemas, a simpler formalism equivalent to XSDs is proposed. It is based on contextual patterns rather than on recursive types and it might serve as a light-weight front end for XML Schema. Next, the effect of EDC on the way XML documents can be typed is discussed. It is argued that a cleaner, more robust, larger but equally feasible class is obtained by replacing EDC with the notion of 1-pass preorder typing (1PPT): schemas that allow one to determine the type of an element of a streaming document when its opening tag is met. This notion can be defined in terms of grammars with restrained competition regular expressions and there is again an equivalent syntactical formalism based on contextual patterns. Finally, algorithms for recognition, simplification, and inclusion of schemas for the various classes are given. |
|||||

BibTeX:
@article{Mart06b, author = {Wim Martens and Frank Neven and Thomas Schwentick and Geert Jan Bex}, title = {Expressiveness and complexity of XML Schema}, journal = {ACM Transactions on Database Systems}, year = {2006}, volume = {31}, number = {3}, pages = {770 - 813}, doi = {http://dx.doi.org/10.1145/1166074.1166076} } |
|||||

Reimann, P., Van den Broeck, C. & Bex, G.J. | A Gaussian model for unsupervised learning | 1996 | J. Phys. A Vol. 29, pp. 3521-3535 |
article | DOI |

Abstract: We consider random patterns on the N-sphere which are uniformly distributed with the exception of a single symmetry-breaking orientation, along which they are Gaussian distributed. The unsupervised recognition of this orientation by different learning rules is studied in the large-N limit using the replica method. The model is simple enough to be analytically tractable and rich enough to exhibit most of the phenomena observed with other pattern distributions. A learning algorithm based on the minimization of a cost function is identified which reaches the upper theoretical limit imposed by the optimal (Bayes-) learning scenario. An implementation of this algorithm is proposed and tested numerically. |
|||||

BibTeX:
@article{Reim96, author = {Peter Reimann and Chris Van den Broeck and Geert Jan Bex}, title = {A Gaussian model for unsupervised learning}, journal = {J. Phys. A}, year = {1996}, volume = {29}, pages = {3521--3535}, doi = {http://dx.doi.org/10.1088/0305-4470/29/13/021} } |
|||||

Van den Broeck, C. & Bex, G.J. | Multifractal a-priori probability distribution for the perceptron | 1998 | Phys. Rev. B Vol. 57(3), pp. 3660-3663 |
article | DOI |

Abstract: We calculate the multifractal spectrum of the a priori probability distribution for a perceptron. |
|||||

BibTeX:
@article{VdBr98, author = {Chris Van den Broeck and Geert Jan Bex}, title = {Multifractal a-priori probability distribution for the perceptron}, journal = {Phys. Rev. B}, year = {1998}, volume = {57}, number = {3}, pages = {3660-3663}, doi = {http://dx.doi.org/10.1103/PhysRevE.57.3660} } |
|||||

Van den Broeck, C. & Bex, G.J. | Self-similarity in networks that learn by example | 1998 | Phil. Mag. B Vol. 77(5), pp. 1479-1486 |
article | DOI |

Abstract: We illustrate how a multifractal analysis, based on numerical results for Boolean networks and analytic results for neural networks, allows us to gain insight into the mechanism by which networks can learn by examples. |
|||||

BibTeX:
@article{VdBr98a, author = {Chris Van den Broeck and Geert Jan Bex}, title = {Self-similarity in networks that learn by example}, journal = {Phil. Mag. B}, year = {1998}, volume = {77}, number = {5}, pages = {1479--1486}, doi = {http://dx.doi.org/10.1080/13642819808205039} } |
|||||

Van Zwieten, K.J., Lambrichts, D., Nackaerts, K., Hauglustaine, S., Schmidt, K., Bex, G.J., Mewis, A., Duyvendak, W., Narain, F., Lamur, K.S., Lippens, P., V., Z.A., Sholukha, V.A., Ivanov, A., Potekhin, V.V., Piskùn, O.E., Varzin, S.A. & Zoubova, I. | Lower arm and hand muscles in focal dystonias - some anatomical and therapeutic aspects [BibTeX] |
2008 | Transactions of the 3rd All-Russian Scientific Practical Conference with international participants ``Health as the basis of human potential : problems and how to solve them'', pp. 353-363 | inproceedings | |

BibTeX:
@inproceedings{vZwi08b, author = {Van Zwieten, Koos Jaap and Lambrichts, Dries and Nackaerts, Katrien and Hauglustaine, Stephan and Schmidt, Klaus and Bex, Geert Jan and Mewis, Alex and Duyvendak, Wim and Narain, Faridi and Lamur, K. S. and Lippens, Peter and Zinkovsky A. V. and Sholukha, V. A. and Ivanov, Alexandre and Potekhin, V. V. and Piskùn, O. E. and Varzin, S. A. and Zoubova, Irina}, title = {Lower arm and hand muscles in focal dystonias - some anatomical and therapeutic aspects}, booktitle = {Transactions of the 3rd All-Russian Scientific Practical Conference with international participants ``Health as the basis of human potential : problems and how to solve them''}, year = {2008}, pages = {353--363} } |
|||||

Westra, R.L., Hollanders, G., Bex, G.J., Gyssens, M. & Tuyls, K. | The identification of dynamic gene-protein networks | 2007 | Vol. 4366Knowledge Discovery and Emergent complexity in bioinformatics, First International Workshop KDECB 2006, Revised selected papers, pp. 157-170 |
inproceedings | DOI |

Abstract: In this study we will focus on piecewise linear state space models for gene-protein interaction networks. We will follow the dynamical systems approach with special interest for partitioned state spaces. From the observation that the dynamics in natural systems tends to punctuated equilibria, we will focus on piecewise linear models and sparse and hierarchic interactions, as, for instance, described by Glass, Kauffman, and de Jong. Next, the paper is concerned with the identification (also known as reverse engineering and reconstruction) of dynamic genetic networks from microarray data. We will describe exact and robust methods for computing the interaction matrix in the special case of piecewise linear models with sparse and hierarchic interactions from partial observations. Finally, we will analyze and evaluate this approach with regard to its performance and robustness towards intrinsic and extrinsic noise. |
|||||

BibTeX:
@inproceedings{West07, author = {Ronald L. Westra and Goele Hollanders and Geert Jan Bex and Marc Gyssens and Karl Tuyls}, title = {The identification of dynamic gene-protein networks}, booktitle = {Knowledge Discovery and Emergent complexity in bioinformatics, First International Workshop KDECB 2006, Revised selected papers}, publisher = {Springer}, year = {2007}, volume = {4366}, pages = {157--170}, doi = {http://dx.doi.org/10.1007/978-3-540-71037-0_11} } |
|||||

Westra, R.L., Hollanders, G., Bex, G.J., Gyssens, M. & Tuyls, K. | The pattern memory of gene-protein networks | 2007 | AI Communications Vol. 20(4), pp. 297-311 |
article | |

Abstract: In this paper we study the potential of gene?protein interaction networks to store input?output patterns. The central question in this study concerns the memory capacity of a network of a given number of genes and proteins, which interact according to a linear state space model with external inputs. Here it is assumed that to a certain combination of inputs there exists an optimal state of the system, i.e., values of the gene expressions and protein levels, that has been attained externally, e.g., through evolutionary learning. Given such a set of learned optimal input?output patterns, the design question here is to find a sparse and hierarchical network structure for the gene?protein interactions and the gene-input couplings. This problem is formulated as an optimization problem in a linear programming setting. Numerical analysis shows that there are clear scale-invariant continuous second-order phase transitions for the network sparsity as the number of patterns increases. These phase transitions divide the system in three regions with different memory characteristics. It is possible to formulate simple scaling rules for the behavior of the network sparsity. Finally, numerical experiments show that these patterns are stable within a certain finite range around the patterns. |
|||||

BibTeX:
@article{West07a, author = {Ronald L. Westra and Goele Hollanders and Geert Jan Bex and Marc Gyssens and Karl Tuyls}, title = {The pattern memory of gene-protein networks}, journal = {AI Communications}, year = {2007}, volume = {20}, number = {4}, pages = {297--311} } |

Created by JabRef on 09/11/2011.