A functional contextual account of background knowledge in categorization: Implications for artificial general intelligence and cognitive accounts of general knowledge

DJ Edwards, C McEnteggart… - Frontiers in …, 2022 - frontiersin.org
Psychology has benefited from an enormous wealth of knowledge about processes of
cognition in relation to how the brain organizes information. Within the categorization …

[HTML][HTML] Extracting knowledge from deep neural networks through graph analysis

VAC Horta, I Tiddi, S Little, A Mileo - Future Generation Computer Systems, 2021 - Elsevier
The popularity of deep learning has increased tremendously in recent years due to its ability
to efficiently solve complex tasks in challenging areas such as computer vision and …

Post-hoc Explanation Options for XAI in Deep Learning: The Insight Centre for Data Analytics Perspective

EM Kenny, ED Delaney, D Greene… - Pattern Recognition. ICPR …, 2021 - Springer
This paper profiles the recent research work on eXplainable AI (XAI), at the Insight Centre for
Data Analytics. This work concentrates on post-hoc explanation-by-example solutions to XAI …

Towards neural network interpretability using commonsense knowledge graphs

Y Ismaeil, D Stepanova, TK Tran… - International Semantic …, 2022 - Springer
Convolutional neural networks (CNNs) classify images by learning intermediate
representations of the input throughout many layers. In recent work, latent representations of …

Generating Local Textual Explanations for CNNs: A Semantic Approach Based on Knowledge Graphs

VAC Horta, A Mileo - International Conference of the Italian Association for …, 2021 - Springer
Abstract Explainable Artificial Intelligence (XAI) has recently become an active research field
due to the need for transparency and accountability when deploying AI models for high …

Explaining cnns using knowledge extraction and graph analysis

VAC Horta, A Mileo - Compendium of Neurosymbolic Artificial …, 2023 - ebooks.iospress.nl
Abstract Explainable Artificial Intelligence (XAI) has recently become an active research field
due to the need for transparency and accountability when deploying AI models for high …

Explaining deep neural networks through knowledge extraction and graph analysis

VAC Horta - 2023 - doras.dcu.ie
Explainable Artificial Intelligence (XAI) has recently become an active research field due to
the need for transparency and accountability when deploying AI models for high-stake …

Knowledge Extraction from Auto-Encoders on Anomaly Detection Tasks Using Co-activation Graphs

D Selani, I Tiddi - Proceedings of the 11th Knowledge Capture …, 2021 - dl.acm.org
Deep neural networks have exploded in popularity and different types of networks are used
to solve a multitude of complex tasks. One such task is anomaly detection, that a type of …