{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:02:48Z","timestamp":1760058168897,"version":"build-2065373602"},"reference-count":23,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,3,16]],"date-time":"2025-03-16T00:00:00Z","timestamp":1742083200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Advancements in the field of artificial intelligence have been rapid in recent years and have revolutionized various industries. Various deep neural network architectures capable of handling both text and images, covering code generation from natural language as well as producing machine translation and text summaries, have been proposed. For example, convolutional neural networks or CNNs perform image classification at a level equivalent to that of humans on many image datasets. These state-of-the-art networks have reached unprecedented levels of success by using complex architectures with billions of parameters, numerous kernel configurations, weight initialization, and regularization methods. Unfortunately to reach this level of success, the models that CNNs use are essentially black box in nature, with little or no human-interpretable information on the decision-making process. This lack of transparency in decision making gave rise to concerns amongst some sectors of the user community such as healthcare, finance, justice, and defense, among others. This challenge motivated our research, where we successfully produced human-interpretable influential features from CNNs for image classification and captured the interactions between these features by producing a concise decision tree making that makes classification decisions. The proposed methodology makes use of a pretrained VGG-16 with fine-tuning to extract feature maps produced by learnt filters. On the CelebA image benchmark dataset, we successfully produced human-interpretable rules that captured the main facial landmarks responsible for segmenting men from women with 89.6% accuracy, while on the more challenging Cats vs. Dogs dataset, the decision tree achieved 87.6% accuracy.<\/jats:p>","DOI":"10.3390\/info16030230","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T06:36:23Z","timestamp":1742193383000},"page":"230","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating Human-Interpretable Rules from Convolutional Neural Networks"],"prefix":"10.3390","volume":"16","author":[{"given":"Russel","family":"Pears","sequence":"first","affiliation":[{"name":"College of Engineering, Computer Science and Engineering, University of North Texas, Denton, TX 76205, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4345-7673","authenticated-orcid":false,"given":"Ashwini Kumar","family":"Sharma","sequence":"additional","affiliation":[{"name":"College of Engineering, Computer Science and Engineering, University of North Texas, Denton, TX 76205, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,16]]},"reference":[{"key":"ref_1","unstructured":"Russell, S., and Norvig, P. (2020). Artificial Intelligence: A Modern Approach, Prentice Hall. [4th ed.]."},{"key":"ref_2","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_4","unstructured":"Jia, D., Wei, D., Richard, S., Li, J.L., Kai, L., and Li, F.-F. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA."},{"key":"ref_5","unstructured":"Krizhevsky, A., and Hinton, G. (2024, February 02). Learning Multiple Layers of Features from Tiny Images. Available online: http:\/\/www.cs.utoronto.ca\/~kriz\/learning-features-2009-TR.pdf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_7","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201323). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/538020a","article-title":"Can we open the black box of AI?","volume":"538","author":"Castelvecchi","year":"2016","journal-title":"Nat. News"},{"key":"ref_10","unstructured":"Das, A., and Rad, P. (2020). Opportunities and challenges in explainable artificial intelligence (xai): A survey. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy should I trust you? \u201d Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_12","first-page":"50","article-title":"European Union regulations on algorithmic decision-making and a \u201cright to explanation\u201d","volume":"38","author":"Goodman","year":"2017","journal-title":"AI Mag."},{"key":"ref_13","first-page":"24","article-title":"Extracting tree-structured representations of trained networks","volume":"8","author":"Craven","year":"1995","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland. Proceedings of the Part I 13."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Oh, S.J., Schiele, B., and Fritz, M. (2019). Towards reverse-engineering black-box neural networks. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, Springer.","DOI":"10.1007\/978-3-030-28954-6_7"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., and Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Achtibat, R., Dreyer, M., Eisenbraun, I., Bosse, S., Wiegand, T., Samek, W., and Lapuschkin, S. (2022). From \u201cwhere\u201d to \u201cwhat\u201d: Towards human-understandable explanations through concept relevance propagation. arXiv.","DOI":"10.1038\/s42256-023-00711-8"},{"key":"ref_19","unstructured":"(2024, February 02). Imagenet Dataset. Available online: https:\/\/image-net.org\/."},{"key":"ref_20","unstructured":"Sharma, A.K. (2024). Human Interpretable Rule Generation from Convolutional Neural Networks Using RICE: Rotation Invariant Contour Extraction. [Master\u2019s Thesis, University of North Texas]."},{"key":"ref_21","unstructured":"Press, W.H., Teukolsky, S.A., Vetterling, W.T., and Flannery, B.P. (1992). Numerical Recipes in C: The Art of Scientific Computing, Cambridge University Press. [2nd ed.]."},{"key":"ref_22","unstructured":"(2024, January 15). Large-Scale CelebFaces Attributes (CelebA) Dataset. Available online: https:\/\/mmlab.ie.cuhk.edu.hk\/projects\/CelebA.html."},{"key":"ref_23","unstructured":"(2024, February 02). Kaggle Cats and Dogs Dataset. Available online: https:\/\/www.microsoft.com\/en-us\/download\/details.aspx?id=54765&msockid=3d36009b0d73606d12a7146f0c7b6140."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/3\/230\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:54:28Z","timestamp":1760028868000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/3\/230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,16]]},"references-count":23,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["info16030230"],"URL":"https:\/\/doi.org\/10.3390\/info16030230","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2025,3,16]]}}}