<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Samatha Ereshi Akkamahadevi</style></author><author><style face="normal" font="default" size="100%">Abhilekha Dalal</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Automating CNN Neuron Interpretation using Concept Induction</style></title><secondary-title><style face="normal" font="default" size="100%">THE 23RD INTERNATIONAL SEMANTIC WEB CONFERENCE, ISWC 2024</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Automation in AI</style></keyword><keyword><style  face="normal" font="default" size="100%">Deep Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Explainable Artificial Intelligence</style></keyword><keyword><style  face="normal" font="default" size="100%">Knowledge Graph</style></keyword><keyword><style  face="normal" font="default" size="100%">Semantic Web</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2024</style></year></dates><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;This paper presents an automation pipeline for interpreting hidden neuron activations in Convolutional Neural Networks (CNNs), a crucial objective of Explainable AI (XAI). Previously, our research group addressed this objective by employing concept induction and semantic reasoning using a concept hierarchy derived from the Wikipedia knowledge graph. However, the process was executed manually, taking several days to complete. In this study, we have fully automated the workflow, achieving consistent results while significantly reducing the execution time. The automation pipeline streamlines model training, data preparation, concept induction, image retrieval, classification, and statistical validation, thereby completely eliminating the manual intervention. This automation enables us to efficiently interpret and validate CNN neuron activations by modifying parameters, such as incorporating a broader range of training images and classes and examining additional concept induction results across various neuron layers using different analytical tools.&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Aaron Eberhart</style></author><author><style face="normal" font="default" size="100%">Michelle Cheatham</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Pseudo-Random ALC Syntax Generation</style></title><secondary-title><style face="normal" font="default" size="100%">The Semantic Web: ESWC 2018 Satellite Events - ESWC 2018 Satellite Events, Heraklion, Crete, Greece, June 3-7, 2018, Revised Selected Papers</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">ALC</style></keyword><keyword><style  face="normal" font="default" size="100%">Description Logic</style></keyword><keyword><style  face="normal" font="default" size="100%">DL</style></keyword><keyword><style  face="normal" font="default" size="100%">random generation</style></keyword><keyword><style  face="normal" font="default" size="100%">synthetic data</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://doi.org/10.1007/978-3-319-98192-5\_4</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">Springer</style></publisher><pub-location><style face="normal" font="default" size="100%">Heraklion, Crete, Greece</style></pub-location><volume><style face="normal" font="default" size="100%">11155</style></volume><pages><style face="normal" font="default" size="100%">19–22</style></pages><isbn><style face="normal" font="default" size="100%">978-3-319-98191-8</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">We discuss a tool capable of rapidly generating pseudo-random syntactically valid ALC expression trees. The program is meant to allow a researcher to create large sets of independently valid expressions with a minimum of personal bias for experimentation.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>10</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Md Kamruzzaman Sarker</style></author><author><style face="normal" font="default" size="100%">Ning Xie</style></author><author><style face="normal" font="default" size="100%">Derek Doran</style></author><author><style face="normal" font="default" size="100%">Michael Raymer</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Explaining Trained Neural Networks with Semantic Web Technologies: First Steps</style></title><secondary-title><style face="normal" font="default" size="100%">Twelveth International Workshop on Neural-Symbolic Learning and Reasoning, NeSy</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Artificial Intelligence</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2017</style></year><pub-dates><date><style  face="normal" font="default" size="100%">07/2017</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://daselab.cs.wright.edu/nesy/NeSy17/</style></url></web-urls></urls><edition><style face="normal" font="default" size="100%">12</style></edition><pub-location><style face="normal" font="default" size="100%">London, UK</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;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.&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Frederick Maier</style></author><author><style face="normal" font="default" size="100%">Yue Ma</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Paraconsistent OWL and Related Logics</style></title><secondary-title><style face="normal" font="default" size="100%">Semantic Web</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Automated Deduction</style></keyword><keyword><style  face="normal" font="default" size="100%">Complexity</style></keyword><keyword><style  face="normal" font="default" size="100%">Description Logic</style></keyword><keyword><style  face="normal" font="default" size="100%">OWL</style></keyword><keyword><style  face="normal" font="default" size="100%">Paraconsistency</style></keyword><keyword><style  face="normal" font="default" size="100%">Semantic Web</style></keyword><keyword><style  face="normal" font="default" size="100%">Web Ontology Language</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2013</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://dx.doi.org/10.3233/SW-2012-0066</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">4</style></volume><pages><style face="normal" font="default" size="100%">395–427</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">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.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>10</ref-type><contributors><secondary-authors><author><style face="normal" font="default" size="100%">Barbara Hammer</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author><author><style face="normal" font="default" size="100%">Wolfgang Maass</style></author><author><style face="normal" font="default" size="100%">Marc Toussaint</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">10302 Abstracts Collection - Learning paradigms in dynamic environments</style></title><secondary-title><style face="normal" font="default" size="100%">Learning paradigms in dynamic environments</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Autonomous learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Dynamic systems</style></keyword><keyword><style  face="normal" font="default" size="100%">Neural-symbolic integration</style></keyword><keyword><style  face="normal" font="default" size="100%">Neurobiology</style></keyword><keyword><style  face="normal" font="default" size="100%">Recurrent neural networks</style></keyword><keyword><style  face="normal" font="default" size="100%">Speech processing</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2010</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://drops.dagstuhl.de/opus/volltexte/2010/2804</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany</style></publisher><pub-location><style face="normal" font="default" size="100%">Dagstuhl, Germany</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Yue Ma</style></author><author><style face="normal" font="default" size="100%">Guilin Qi</style></author><author><style face="normal" font="default" size="100%">Guohui Xiao</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author><author><style face="normal" font="default" size="100%">Zuoquan Lin</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Computational Complexity and Anytime Algorithm for Inconsistency Measurement</style></title><secondary-title><style face="normal" font="default" size="100%">International Journal of Software and Informatics</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">algorithm</style></keyword><keyword><style  face="normal" font="default" size="100%">computational complexity</style></keyword><keyword><style  face="normal" font="default" size="100%">inconsistency measurement</style></keyword><keyword><style  face="normal" font="default" size="100%">Knowledge representation</style></keyword><keyword><style  face="normal" font="default" size="100%">multi-valued logic</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2010</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://www.ijsi.org/ch/reader/view_abstract.aspx?file_no=i41&amp;flag=1</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">4</style></volume><pages><style face="normal" font="default" size="100%">3–21</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p class=&quot;rtejustify&quot;&gt;Measuring 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&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author><author><style face="normal" font="default" size="100%">Frank van Harmelen</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A Reasonable Semantic Web</style></title><secondary-title><style face="normal" font="default" size="100%">Semantic Web</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Automated Reasoning</style></keyword><keyword><style  face="normal" font="default" size="100%">Formal Semantics</style></keyword><keyword><style  face="normal" font="default" size="100%">Knowledge representation</style></keyword><keyword><style  face="normal" font="default" size="100%">Linked Open Data</style></keyword><keyword><style  face="normal" font="default" size="100%">Semantic Web</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2010</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://dx.doi.org/10.3233/SW-2010-0010</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">1</style></volume><pages><style face="normal" font="default" size="100%">39–44</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p class=&quot;rtejustify&quot;&gt;The 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 &quot;shared inference,&quot; 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.&lt;/p&gt;
</style></abstract></record></records></xml>