City Research Online

Extracting Meaningful High-Fidelity Knowledge from Convolutional Neural Networks

Ngan, K. H., Garcez, A. & Townsend, J. (2022). Extracting Meaningful High-Fidelity Knowledge from Convolutional Neural Networks. In: 2022 International Joint Conference on Neural Networks (IJCNN). 2022 International Joint Conference on Neural Networks (IJCNN), 18-23 Jul 2022, Padua, Italy. doi: 10.1109/ijcnn55064.2022.9892194


Convolutional Neural Networks (CNNs) have been widely used for complex image recognition tasks. Due to the highly entangled correlations learned by the latent features in the convolutional kernels of CNNs, deriving human-comprehensible knowledge from CNNs has been proven difficult. As such, reasoning from relationships between kernels has been limited, resulting in little knowledge transfer from one task to another related task learned by CNNs. This paper introduces a neural-symbolic approach for providing semantically meaningful explanations to CNNs using logical rules and a shared conceptual representation space to capture the meaning of the knowledge learned. The validity of the proposed approach is demonstrated using benchmark chest x-rays of two respiratory conditions: pleural effusion and COVID-19. Our results show empirically that symbolic rules can be associated with semantically meaningful explanations obtained from different but related CNN models, even in domains requiring specialised knowledge such as medical imaging. This work is expected to aid the analysis of black-box CNNs by associating the predictions obtained from the CNNs with clinical research findings.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Publisher Keywords: Neural-Symbolic Integration, Convolutional Neural Networks, Concept Representation, Knowledge Sharing, Medical Imaging
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Departments: School of Science & Technology
School of Science & Technology > Computer Science
SWORD Depositor:
[thumbnail of IJCNN_Draft__Master_.pdf]
Text - Accepted Version
Download (36MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login