The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.

%B Twelveth International Workshop on Neural-Symbolic Learning and Reasoning, NeSy %7 12 %C London, UK %8 07/2017 %G eng %U http://daselab.cs.wright.edu/nesy/NeSy17/ %0 Journal Article %J Semantic Web %D 2013 %T Paraconsistent OWL and Related Logics %A Frederick Maier %A Yue Ma %A Pascal Hitzler %K Automated Deduction %K Complexity %K Description Logic %K OWL %K Paraconsistency %K Semantic Web %K Web Ontology Language %X The Web Ontology Language OWL is currently the most prominent formalism for representing ontologies in Semantic Web applications. OWL is based on description logics, and automated reasoners are used to infer knowledge implicitly present in OWL ontologies. However, because typical description logics obey the classical principle of explosion, reasoning over inconsistent ontologies is impossible in OWL. This is so despite the fact that inconsistencies are bound to occur in many realistic cases, e.g., when multiple ontologies are merged or when ontologies are created by machine learning or data mining tools. In this paper, we present four-valued paraconsistent description logics which can reason over inconsistencies. We focus on logics corresponding to OWL DL and its profiles. We present the logic SROIQ4, showing that it is both sound relative to classical SROIQ and that its embedding into SROIQ is consequence preserving. We also examine paraconsistent varieties of EL++, DL-Lite, and Horn-DLs. The general framework described here has the distinct advantage of allowing classical reasoners to draw sound but nontrivial conclusions from even inconsistent knowledge bases. Truth-value gaps and gluts can also be selectively eliminated from models (by inserting additional axioms into knowledge bases). If gaps but not gluts are eliminated, additional classical conclusions can be drawn without affecting paraconsistency. %B Semantic Web %V 4 %P 395–427 %G eng %U http://dx.doi.org/10.3233/SW-2012-0066 %R 10.3233/SW-2012-0066 %0 Conference Proceedings %B Learning paradigms in dynamic environments %D 2010 %T 10302 Abstracts Collection - Learning paradigms in dynamic environments %E Barbara Hammer %E Pascal Hitzler %E Wolfgang Maass %E Marc Toussaint %K Autonomous learning %K Dynamic systems %K Neural-symbolic integration %K Neurobiology %K Recurrent neural networks %K Speech processing %B Learning paradigms in dynamic environments %I Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany %C Dagstuhl, Germany %G eng %U http://drops.dagstuhl.de/opus/volltexte/2010/2804 %0 Journal Article %J International Journal of Software and Informatics %D 2010 %T Computational Complexity and Anytime Algorithm for Inconsistency Measurement %A Yue Ma %A Guilin Qi %A Guohui Xiao %A Pascal Hitzler %A Zuoquan Lin %K algorithm %K computational complexity %K inconsistency measurement %K Knowledge representation %K multi-valued logic %XMeasuring inconsistency degrees of inconsistent knowledge bases is an important problem as it provides context information for facilitating inconsistency handling. Many methods have been proposed to solve this problem and a main class of them is based on some kind of paraconsistent semantics. In this paper, we consider the computational aspects of inconsistency degrees of propositional knowledge bases under 4-valued semantics. We first give a complete analysis of the computational complexity of computing inconsistency degrees. As it turns out that computing the exact inconsistency degree is intractable, we then propose an anytime algorithm that provides tractable approximations of the inconsistency degree from above and below. We show that our algorithm satisfies some desirable properties and give experimental results of our implementation of the algorithm

%B International Journal of Software and Informatics %V 4 %P 3–21 %G eng %U http://www.ijsi.org/ch/reader/view_abstract.aspx?file_no=i41&flag=1 %0 Journal Article %J Semantic Web %D 2010 %T A Reasonable Semantic Web %A Pascal Hitzler %A Frank van Harmelen %K Automated Reasoning %K Formal Semantics %K Knowledge representation %K Linked Open Data %K Semantic Web %XThe realization of Semantic Web reasoning is central to substantiating the Semantic Web vision. However, current mainstream research on this topic faces serious challenges, which forces us to question established lines of research and to rethink the underlying approaches. We argue that reasoning for the Semantic Web should be understood as "shared inference," which is not necessarily based on deductive methods. Model-theoretic semantics (and sound and complete reasoning based on it) functions as a gold standard, but applications dealing with large-scale and noisy data usually cannot afford the required runtimes. Approximate methods, including deductive ones, but also approaches based on entirely different methods like machine learning or natureinspired computing need to be investigated, while quality assurance needs to be done in terms of precision and recall values (as in information retrieval) and not necessarily in terms of soundness and completeness of the underlying algorithms.

%B Semantic Web %V 1 %P 39–44 %G eng %U http://dx.doi.org/10.3233/SW-2010-0010 %R 10.3233/SW-2010-0010