Towards explainable deep neural networks (xDNN)
Open accessAbstract
In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers an explainable internal architecture that can outperform the existing methods, requires very little computational resources (no need for GPUs) and short training times (in the order of seconds). The proposed approach, xDNN is using prototypes. Prototypes are actual training data samples (images), which are local peaks of the empirical data distribution called typicality as well as of the data density. This generative model is identified in a closed form and equates to the pdf but is derived automatically and entirely from the training data with no user- or problem-specific thresholds, parameters or intervention. The proposed xDNN offers a new deep learning architecture that combines reasoning and learning in a synergy. It is non-iterative and non-parametric, which explains its efficiency in terms of time and computational resources. From the user perspective, the proposed approach is clearly understandable to human users. We tested it on challenging problems as the classification of different lighting conditions for driving scenes (iROADS), object detection (Caltech-256, and Caltech-101), and SARS-CoV-2 identification via computed tomography scan (COVID CT-scans dataset). xDNN outperforms the other methods including deep learning in terms of accuracy, time to train and offers an explainable classifier.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Including several layers in a neural network makes it difficult for designers to explain how the algorithm reached a particular prediction.
“Inclusion of several layers in a neural network makes it difficult for designers to explain how the algorithm has reached a particular prediction outcome [1].”
From Explainable AI (XAI): Core Ideas, Techniques, and Solutions (2023) · cites this paper as [1]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
Quinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439 · see citing works
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · see citing works
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · see citing works
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971 · see citing works
(2016) · Cited by 11,679 · see citing works
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · see citing works
Least Squares Support Vector Machine Classifiers
Suykens, J., & Vandewalle, J. (1999) · Neural Processing Letters · doi:10.1023/a:1018628609742 · Cited by 9,481 · see citing works
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · see citing works
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121 · see citing works
Fei-Fei, L., Fergus, R., & Perona, P. (2007) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2005.09.012 · Cited by 2,359 · see citing works
(2007) · CaltechAUTHORS (California Institute of Technology) · Cited by 2,274 · see citing works
Hastie, T. J., Rosset, S., Zhu, J., & Zou, H. (2009) · Statistics and Its Interface · doi:10.4310/sii.2009.v2.n3.a8 · Cited by 1,907 · see citing works
The Microsoft 2017 Conversational Speech Recognition System
Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., & Stolcke, A. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461870 · Cited by 472 · see citing works
Object Detection Networks on Convolutional Feature Maps
Ren, S., He, K., Girshick, R., Zhang, X., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2601099 · Cited by 454 · see citing works
Sejnowski, T. J. (2018) · doi:10.7551/mitpress/11474.001.0001 · Cited by 438 · see citing works
Supervised Representation Learning: Transfer Learning with Deep Autoencoders
Zhuang, F., Cheng, X., Luo, P., Pan, S. J., & He, Q. (2016) · Cited by 320 · see citing works
Hu, J., Lu, J., & Tan, Y. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298629 · Cited by 229 · see citing works
Autonomous learning systems: from data streams to knowledge in real-time
(2013) · Choice Reviews Online · doi:10.5860/choice.51-0926 · Cited by 165 · see citing works
Architectural Study of HOG Feature Extraction Processor for Real-Time Object Detection
Mizuno, K., Terachi, Y., Takagi, K., et al. (2012) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips.2012.57 · Cited by 150 · see citing works
Empirical Approach to Machine Learning
Angelov, P. P., & Gu, X. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-02384-3 · Cited by 99 · see citing works
Self-citationClassifying web videos using a global video descriptor
Solmaz, B., Assari, S. M., & Shah, M. A. (2012) · Machine Vision and Applications · doi:10.1007/s00138-012-0449-x · Cited by 93 · see citing works
A Generalized Methodology for Data Analysis
Angelov, P. P., Gu, X., & Príncipe, J. C. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2753880 · Cited by 73 · see citing works
Self-citationMemory-Efficient Deep Learning on a SpiNNaker 2 Prototype
Liu, C., Bellec, G., Vogginger, B., Kappel, D., Partzsch, J., Neumärker, F., Höppner, S., Maass, W., Furber, S. B., Legenstein, R. A., et al. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00840 · Cited by 70 · see citing works
Deep rule-based classifier with human-level performance and characteristics
Angelov, P. P., & Gu, X. (2018) · Information Sciences · doi:10.1016/j.ins.2018.06.048 · Cited by 68 · see citing works
Self-citationVehicle Detection Based on Multi-feature Clues and Dempster-Shafer Fusion Theory
Rezaei, M., & Terauchi, M. (2013) · Pacific-Rim Symposium on Image and Video Technology · doi:10.1007/978-3-642-53842-1_6 · Cited by 38 · see citing works
Cao, J., Wang, M., Li, Y., et al. (2019) · PLoS ONE · doi:10.1371/journal.pone.0215136 · Cited by 34 · see citing works
Types of (dis-)similarities and adaptive mixtures thereof for improved classification learning
Nebel, D., Kaden, M., Villmann, A., et al. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.12.091 · Cited by 25 · see citing works
Context-aware attention network for image recognition
Leng, J., Liu, Y., & Shang, C. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04281-y · Cited by 17 · see citing works
Novelty Detection and Learning from Extremely Weak SupervisionPreprint
Soares, E. A., & Angelov, P. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00616 · Cited by 6 · see citing works
Self-citationSingle-label and multi-label conceptor classifiers in pre-trained neural networks
Qian, G., Zhang, L., & Wang, Y. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3432-2 · Cited by 5 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [26][26] E. Soares, P. Angelov, B. Costa, and M. Castro, 'Actively semisupervised deep rule-based classifier applied to adverse driving scenarios,' in 2019 International Joint Conference on Neural Networks (IJCNN) . IEEE, 2019, pp. 1-8. -
Cited by
Sorted by citations
Explainable AI (XAI): Core Ideas, Techniques, and Solutions
Dwivedi, R., Dave, D., Naik, H., Singhal, S., Omer, R., Patel, P., Qian, B., Wen, Z., Shah, T., Morgan, G., et al. (2023) · ACM Computing Surveys · doi:10.1145/3561048 · Cited by 1,386 · see citing works
A Survey on the Explainability of Supervised Machine Learning
Burkart, N., & Huber, M. F. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12228 · Cited by 1,008 · see citing works
Explainable artificial intelligence: a comprehensive review
Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10088-y · Cited by 983 · see citing works
Interpretable machine learning: Fundamental principles and 10 grand challenges
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2022) · Statistics Surveys · doi:10.1214/21-ss133 · Cited by 958 · see citing works
Explainable artificial intelligence: an analytical review
Angelov, P. P., Soares, E. A., Jiang, R., Arnold, N. I., & Atkinson, P. M. (2021) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1424 · Cited by 843 · see citing works
Self-citationSurvey of Explainable AI Techniques in Healthcare
Chaddad, A., Peng, J., Xu, J., & Bouridane, A. (2023) · Sensors · doi:10.3390/s23020634 · Cited by 591 · see citing works
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612 · see citing works
“For example, previous research has embedded linear models and prototype selection to the DNN [16, 20, 73].”
MethodInfluentialA survey of visual analytics for Explainable Artificial Intelligence methods
Alicioglu, G., & Sun, B. (2022) · Computers & Graphics · doi:10.1016/j.cag.2021.09.002 · Cited by 221 · see citing works
Applications of artificial intelligence in battling against covid-19: A literature review
Tayarani N., M.-H. (2021) · Chaos, Solitons & Fractals · doi:10.1016/j.chaos.2020.110338 · Cited by 210 · see citing works
Lu, S., Zhu, Z., Gorriz, J. M., Wang, S., & Zhang, Y. (2022) · International Journal of Intelligent Systems · doi:10.1002/int.22686 · Cited by 151 · see citing works
A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research
Watson, C., Cooper, N., Palacio, D. N., Moran, K., & Poshyvanyk, D. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3485275 · Cited by 137 · see citing works
Futia, G., & Vetrò, A. (2020) · Information · doi:10.3390/info11020122 · Cited by 94 · see citing works
Maarif, M. R., Saleh, A. R., Habibi, M., Fitriyani, N. L., & Syafrudin, M. (2023) · Information · doi:10.3390/info14050265 · Cited by 58 · see citing works
- Authors
- Angelov, P., & Soares, E.
- Affiliations
- Lancaster University (GB)
- Corresponding author
- Soares, Eduardo
- Venue
- Neural Networks
- Publisher
- Elsevier BV
- Published
- 2020-10
- Volume
- 130
- Pages
- 185-194
- ISSN
- 0893-6080 (ISSN-L)
- OpenAlex
- W2993468200
- Cited by
- 292
- References
- 35
- Citations by year
- 2026: 18 · 2025: 36 · 2024: 57 · 2023: 64 · 2022: 56 · 2021: 45 · 2020: 16
- FWCI
- 17.63
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Neural Networks (publishedVersion)
- PubMed (publishedVersion)
- Lancaster EPrints (Lancaster University) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- Lancaster EPrints (Lancaster University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- explainable deep neural networks, prototype learning, typicality, data density, object detection
- MeSH terms
- Deep Learning, COVID-19, Humans, Image Processing, Computer-Assisted, Pneumonia, Viral, Tomography, X-Ray Computed, Coronavirus Infections, Pandemics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
