<?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%">Avishek Das</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%">Hidden Neuron Activation Analysis on Labeled Text Data</style></title><secondary-title><style face="normal" font="default" size="100%">K-CAP '25: Knowledge Capture Conference 2025</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Concept-based Explanation</style></keyword><keyword><style  face="normal" font="default" size="100%">Dense Layer Analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">Explainable AI</style></keyword><keyword><style  face="normal" font="default" size="100%">Hidden Neuron Analysis</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2025</style></year><pub-dates><date><style  face="normal" font="default" size="100%">12/2025</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">ACM</style></publisher><pub-location><style face="normal" font="default" size="100%">USA</style></pub-location><pages><style face="normal" font="default" size="100%">206 - 210</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Understanding the internal mechanisms of deep neural networks remains a central challenge in the field of Explainable Artificial Intelligence (XAI). With the rapid advancement of neural architectures in natural language processing (NLP), analyzing the role of hidden neurons in capturing and processing linguistic features has become increasingly important. This study investigates Hidden Neuron Activation Analysis on labeled text data to reveal how individual neurons contribute to a model’s decision-making process. We propose a model-agnostic explainability framework for text classifiers that identifies concepts activating specific neurons involved in classification. An LSTM-based network is trained on the AG News topic classification dataset, comprising four distinct classes, and the final Dense layer with 64 neurons was analyzed. In addition, statistical analyses like the Mann-Whitney U Test is conducted to assess the robustness and reliability of the system. The statistical analysis shows that, concepts plays important role in the decision making process of neural network. Our findings enhance interpretability in NLP models and offer a foundation for optimizing neural architectures in text classification tasks.&lt;/p&gt;
</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%">Abhilekha Dalal</style></author><author><style face="normal" font="default" size="100%">Rushrukh Rayan</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%">Error-margin Analysis for Hidden Neuron Activation Labels</style></title><secondary-title><style face="normal" font="default" size="100%">18th International Conference on Neural-Symbolic Learning and Reasoning, NeSy 2024</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">CNN</style></keyword><keyword><style  face="normal" font="default" size="100%">Concept Induction</style></keyword><keyword><style  face="normal" font="default" size="100%">Explainable AI</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2024</style></year></dates><publisher><style face="normal" font="default" size="100%">Springer </style></publisher><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Understanding how high-level concepts are represented with- in artificial neural networks is a fundamental challenge in the field of arti- ficial intelligence. While existing literature in explainable AI emphasizes the importance of labeling neurons with concepts to understand their functioning, they mostly focus on identifying what stimulus activates a neuron in most cases; this corresponds to the notion of recall in informa- tion retrieval. We argue that this is only the first-part of a two-part job; it is imperative to also investigate neuron responses to other stimuli, i.e., their precision. We call this the neuron label’s error margin.&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%">Abhilekha Dalal</style></author><author><style face="normal" font="default" size="100%">Rushrukh Rayan</style></author><author><style face="normal" font="default" size="100%">Adrita Barua</style></author><author><style face="normal" font="default" size="100%">Eugene Y. Vasserman</style></author><author><style face="normal" font="default" size="100%">Kamruzzaman Sarker</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%">On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis</style></title><secondary-title><style face="normal" font="default" size="100%">18th International Conference on Neural-Symbolic Learning and Reasoning, NeSy 2024</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">CNN</style></keyword><keyword><style  face="normal" font="default" size="100%">Concept Induction</style></keyword><keyword><style  face="normal" font="default" size="100%">Explainable AI</style></keyword><keyword><style  face="normal" font="default" size="100%">LLM</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2024</style></year></dates><publisher><style face="normal" font="default" size="100%">Springer </style></publisher><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;We introduce a novel model-agnostic post-hoc Explainable AI method that provides meaningful interpretations for hidden neuron activations in a Convolutional Neural Network. Our approach uses a Wikipedia-derived concept hierarchy with approx. 2 million classes as background knowledge, and deductive reasoning based Concept Induc- tion for explanation generation. Additionally, we explore and compare the capabilities of off-the-shelf pre-trained multimodal-based explainable methods. Our evaluation shows that our neurosymbolic method holds a competitive edge in both quantitative and qualitative aspects.&lt;/p&gt;
</style></abstract></record></records></xml>