<?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></records></xml>