Explaining deep neural networks: A survey on the global interpretation methods

Journal article


Saleem, R., Yuan, B., Kurugollu, F., Anjum, A. and Liu, L. 2022. Explaining deep neural networks: A survey on the global interpretation methods. Neurocomputing. 513, pp. 165-180. https://doi.org/10.1016/j.neucom.2022.09.129
AuthorsSaleem, R., Yuan, B., Kurugollu, F., Anjum, A. and Liu, L.
Abstract

A substantial amount of research has been carried out in Explainable Artificial Intelligence (XAI) models,
especially in those which explain the deep architectures of neural networks. A number of XAI approaches have been proposed to achieve trust in Artificial Intelligence (AI) models as well as provide explainability of specific decisions made within these models. Among these approaches, global interpretation methods have emerged as the prominent methods of explainability because they have the strength to explain every feature and the structure of the model. This survey attempts to provide a comprehensive review
of global interpretation methods that completely explain the behaviour of the AI models. We present a taxonomy of the available global interpretations models and systematically highlight the critical features and algorithms that differentiate them from local as well as hybrid models of explainability. Through examples and case studies from the literature, we evaluate the strengths and weaknesses of the global interpretation models and assess challenges when these methods are put into practice. We conclude the paper by providing the future directions of research in how the existing challenges in global interpretation methods could be addressed and what values and opportunities could be realized by the resolution
of these challenges.

KeywordsArtificial intelligence; Deep neural networks; Black box Models; Explainable artificial intelligence; Global interpretation
Year2022
JournalNeurocomputing
Journal citation513, pp. 165-180
PublisherElseiver
ISSN 1872-8286
Digital Object Identifier (DOI)https://doi.org/10.1016/j.neucom.2022.09.129
Web address (URL)https://www.sciencedirect.com/science/article/pii/S0925231222012218?via%3Dihub
Accepted author manuscript
License
File Access Level
Open
Publisher's version
License
File Access Level
Open
Output statusPublished
Publication dates
Online23 Sep 2022
Publication process dates
Accepted15 Sep 2022
Deposited28 Oct 2022
Permalink -

https://repository.derby.ac.uk/item/9qw2z/explaining-deep-neural-networks-a-survey-on-the-global-interpretation-methods

Download files


Publisher's version
  • 9
    total views
  • 0
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Export as

Related outputs

A unified graph model based on molecular data binning for disease subtyping
Hassan Zada, M., Yuan, B, Khan, W., Anjum, A., Reiff-Marganiec, S. and Saleem, R. 2022. A unified graph model based on molecular data binning for disease subtyping. Journal of Biomedical Informatics. pp. 1-24. https://doi.org/10.1016/j.jbi.2022.104187
Severity Estimation of Plant Leaf Diseases Using Segmentation Method
Entuni, Chyntia Jaby, Afendi Zulcaffle, Tengku Mohd, Kipli, Kuryati and Kurugollu, Fatih 2020. Severity Estimation of Plant Leaf Diseases Using Segmentation Method. Applied Science and Engineering Progress. 14 (1), pp. 108-119. https://doi.org/10.14416/j.asep.2020.11.004
Explaining probabilistic Artificial Intelligence (AI) models by discretizing Deep Neural Networks
Saleem, Rabia, Yuan, Bo, Kurugollu, Fatih and Anjum, Ashiq 2020. Explaining probabilistic Artificial Intelligence (AI) models by discretizing Deep Neural Networks. IEEE. https://doi.org/10.1109/ucc48980.2020.00070
NOTRINO: a NOvel hybrid TRust management scheme for INternet-Of-vehicles
Ahmad, F., Kurugollu, Fatih, Kerrache, Chaker Abdelaziz, Sezer, Sakir and Liu, Lu 2021. NOTRINO: a NOvel hybrid TRust management scheme for INternet-Of-vehicles. IEEE Transactions on Vehicular Technology. https://doi.org/10.1109/TVT.2021.3049189
A Novel Security Methodology for Smart Grids: A Case Study of Microcomputer-Based Encryption for PMU Devices
Varan, Metin, Akgul, Akif, Kurugollu, Fatih, Sansli, Ahmet and Smith, K. 2021. A Novel Security Methodology for Smart Grids: A Case Study of Microcomputer-Based Encryption for PMU Devices. Complexity. 2021, pp. 1-15. https://doi.org/10.1155/2021/2798534
Persation: an IoT based personal safety prediction model aided solution
Alofe, Olasunkanmi Matthew, Fatema, Kaniz, Azad, Muhammad Ajmal and Kurugollu, Fatih 2020. Persation: an IoT based personal safety prediction model aided solution. International Journal of Computing and Digital Systems.
MARINE: Man-in-the-middle attack resistant trust model IN connEcted vehicles
Ahmad, F., Kurugollu, Fatih, Adnane, Asma, Hussain, Rasheed and Hussain, Fatima 2020. MARINE: Man-in-the-middle attack resistant trust model IN connEcted vehicles. IEEE Internet of Things. https://doi.org/10.1109/JIOT.2020.2967568
CRT-BIoV: A cognitive radio technique for blockchain-enabled internet of vehicles
Rathee, Geetanjali, Ahmad, F., Kurugollu, Fatih, Azad, Muhammad, Iqbal, Razi and Imran, Muhammad 2020. CRT-BIoV: A cognitive radio technique for blockchain-enabled internet of vehicles. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/TITS.2020.3004718
Vehicular sensor networks: Applications, advances and challenges
Kurugollu, Fatih, Ahmed, Syed Hassan, Hussain, Rasheed, Ahmad, F. and Kerrache, Chaker Abdelaziz 2020. Vehicular sensor networks: Applications, advances and challenges. Sensors. https://doi.org/10.3390/s20133686
Spatio-temporal rich model-based video steganalysis on cross sections of motion vector planes
Tasdemir, Kasim, Kurugollu, Fatih and Sezer, Sakir 2016. Spatio-temporal rich model-based video steganalysis on cross sections of motion vector planes. IEEE Transactions on Image Processing. https://doi.org/10.1109/TIP.2016.2567073
Cascaded multimodal biometric recognition framework
Albesher, Badr, Kurugollu, Fatih, Bouridane, Ahmed and Baig, Asim 2013. Cascaded multimodal biometric recognition framework. IET Biometrics. https://doi.org/10.1049/iet-bmt.2012.0043
Privacy region protection for H.264/AVC with enhanced scrambling effect and a low bitrate overhead
Wang, Yongsheng, O׳Neill, Máire, Kurugollu, Fatih and O׳Sullivan, Elizabeth 2015. Privacy region protection for H.264/AVC with enhanced scrambling effect and a low bitrate overhead. Signal Processing: Image Communication. https://doi.org/10.1016/j.image.2015.04.013
Blind image watermark detection algorithm based on discrete shearlet transform using statistical decision theory
Ahmaderaghi, Baharak, Kurugollu, Fatih, Rincon, Jesus Martinez Del and Bouridane, Ahmed 2018. Blind image watermark detection algorithm based on discrete shearlet transform using statistical decision theory. IEEE Transactions on Computational Imaging. https://doi.org/10.1109/TCI.2018.2794065
Frontal view gait recognition with fusion of depth features from a time of flight camera
Afendi Tengku Mohd, Kurugollu, Fatih, Crookes, Danny, Bouridane, Ahmed and Farid, Mohsen 2018. Frontal view gait recognition with fusion of depth features from a time of flight camera. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/TIFS.2018.2870594
Towards a trusted unmanned aerial system using blockchain (BUAS) for the protection of critical infrastructure
Barka, Ezedin, Kerrache, Chaker Abdelaziz, Benkraouda, Hadjer, Shuaib, Khaled, Ahmad, F. and Kurugollu, Fatih 2019. Towards a trusted unmanned aerial system using blockchain (BUAS) for the protection of critical infrastructure. Transactions on Emerging Telecommunications Technologies. https://doi.org/10.1002/ett.3706
A comparative analysis of trust models for safety applications in IoT-enabled vehicular networks
Ahmad, F., Adnane, Asma, Hussain, Rasheed and Kurugollu, Fatih 2019. A comparative analysis of trust models for safety applications in IoT-enabled vehicular networks. IEEE.
A survey of deep learning solutions for multimedia visual content analysis.
Nadeem, Muhammad Shahroz, Franqueira, Virginia N. L., Zhai, Xiaojun and Kurugollu, Fatih 2019. A survey of deep learning solutions for multimedia visual content analysis. IEEE Access. https://doi.org/10.1109/ACCESS.2019.DOI
Realization of blockchain in named data networking-based internet-of-vehicles
Ahmad, F., Kerrache, Chaker Abdelaziz, Kurugollu, Fatih and Hussain, Rasheed 2019. Realization of blockchain in named data networking-based internet-of-vehicles. IT Professional. https://doi.org/10.1109/MITP.2019.2912142
Spatio-temporal rich model-based video steganalysis on cross sections of motion vector planes.
Tasdemir, Kasim, Kurugollu, Fatih and Sezer, Sakir 2016. Spatio-temporal rich model-based video steganalysis on cross sections of motion vector planes. IEEE Transactions on Image Processing. https://doi.org/10.1109/TIP.2016.2567073
Man-In-The-Middle attacks in Vehicular Ad-Hoc Networks: Evaluating the impact of attackers’ strategies.
Ahmad, F., Adnane, Asma, Franqueira, Virginia N. L., Kurugollu, Fatih and Liu, Lu 2018. Man-In-The-Middle attacks in Vehicular Ad-Hoc Networks: Evaluating the impact of attackers’ strategies. Sensors. 18 (11), p. 4040. https://doi.org/10.3390/s18114040
Digital video source identification based on green-channel photo response non-uniformity (G-PRNU)
Al-Athamneh, Mohammad, Kurugollu, Fatih, Crookes, Danny and Farid, Mohsen 2016. Digital video source identification based on green-channel photo response non-uniformity (G-PRNU). https://doi.org/10.5121/csit.2016.61105