{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:08:26Z","timestamp":1760058506793,"version":"build-2065373602"},"reference-count":31,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>A vital area of AI is the ability of a model to recognise the limits of its knowledge and flag when presented with something unclassifiable instead of making incorrect predictions. It has often been claimed that probabilistic networks, particularly Bayesian neural networks, are unsuited to this problem due to unknown data, meaning that the denominator in Bayes\u2019 equation would be incalculable. This study challenges this view, approaching the task as a blended problem, by considering unknowns to be highly corrupted data, and creating adequate working spaces and generalizations. The core of this method lies in structuring the network in such a manner as to target the high and low confidence levels of the predictions. Instead of simply adjusting for low confidence, developing a consistent gap in the confidence in class predictions between known image types and unseen, unclassifiable data new datapoints can be accurately identified and unknown inputs flagged accordingly through averaged thresholding. In this way, the model is also self-reflecting, using the uncertainties for all data rather than just the unknown subsections in order to determine the limits of its knowledge. The results show that these models are capable of strong performance on a variety of image datasets, with levels of accuracy, recall, and prediction gap consistency across a range of openness levels similar to those achieved using traditional methods.<\/jats:p>","DOI":"10.3390\/bdcc9040095","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T11:26:41Z","timestamp":1744284401000},"page":"95","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bayesian Deep Neural Networks with Agnostophilic Approaches"],"prefix":"10.3390","volume":"9","author":[{"given":"Sarah","family":"McDougall","sequence":"first","affiliation":[{"name":"School of Computing, Goldsmiths, University of London, New Cross, London SE14 6NW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2066-4222","authenticated-orcid":false,"given":"Sarah","family":"Rauchas","sequence":"additional","affiliation":[{"name":"School of Computing, Goldsmiths, University of London, New Cross, London SE14 6NW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vahid","family":"Rafe","sequence":"additional","affiliation":[{"name":"Center for Software Reliability, Department of Computing, City St George\u2019s, University of London, London EC1V 0HB, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3614","DOI":"10.1109\/TPAMI.2020.2981604","article-title":"Recent Advances in Open Set Recognition: A Survey","volume":"43","author":"Geng","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","unstructured":"MSalehi, M., Mirzaei, H., Hendrycks, D., Li, Y., Rohban, M.H., and Sabokrou, M. (2021). A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pang, G., Shen, C., Hengel, A., and Cao, L. (2021, January 14\u201318). Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Singapore.","DOI":"10.1145\/3447548.3467417"},{"key":"ref_4","first-page":"205","article-title":"Deep Learning based Anomaly Detection in Images: Insights, Challenges and Recommendations","volume":"12","author":"Alloqmani","year":"2021","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_5","unstructured":"Chopra, P. (2025, April 01). Bayesian NNs Using Pyro and PyTorch. TDS, 27 November 2018. Available online: https:\/\/medium.com\/data-science\/making-your-neural-network-say-i-dont-know-bayesian-nns-using-pyro-and-pytorch-b1c24e6ab8cd."},{"key":"ref_6","unstructured":"Fan, W., Miller, M., Stolfo, S., Lee, W., and Chan, P. (December, January 29). Using Artificial Anomalies to Detect Unknown and Known Network Intrusions. Proceedings of the 2001 IEEE International Conference on Data Mining, San Jose, CA, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, X., Fei, J., Xie, J., Li, D., Jiang, H., Wang, R., and Qi, Z. (2023). Open Set Recognition for Malware Traffic via Predictive Uncertainty. Electronics, 12.","DOI":"10.3390\/electronics12020323"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., and Clune, J. (2015, January 7\u201312). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref_9","unstructured":"Chollet, F. (2018). Deep Learning with Python, Manning Publications."},{"key":"ref_10","unstructured":"Rosebrock, A. (2024, September 12). Anomaly Detection with Keras, TensorFlow, and Deep Learning. Pyimagesearch, Available online: https:\/\/pyimagesearch.com\/2020\/03\/02\/anomaly-detection-with-keras-tensorflow-and-deep-learning\/."},{"key":"ref_11","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and LeCun, Y. (2014, January 12\u201314). OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. Proceedings of the 2nd International Conference on Learning Representations, Banff, AB, Canada."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/TIT.1970.1054406","article-title":"On optimum recognition error and reject tradeoff","volume":"16","author":"Chow","year":"1970","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_13","unstructured":"Grandvalet, Y., Rakotomamonjy, A., Keshet, J., and Canu, S. (2009). Support vector machines with a reject option. Advances in Neural Information Processing Systems, Morgan Kaufmann Publishers Inc."},{"key":"ref_14","unstructured":"Geifman, Y., and Ran, E.Y. (2017). Selective classification for deep neural networks. Advances in Neural Information Processing Systems, Morgan Kaufmann Publishers Inc."},{"key":"ref_15","unstructured":"(2024, September 10). TensorFlow. mnist_corrupted. TensorFlow, 2022 (Updated). Available online: https:\/\/www.tensorflow.org\/datasets\/catalog\/mnist_corrupted."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"562","DOI":"10.3390\/signals5030031","article-title":"Understanding How Image Quality Affects Transformer Neural Networks","volume":"5","author":"Varga","year":"2024","journal-title":"Signals"},{"key":"ref_17","unstructured":"Kang, C. (2024, September 10). Bayesian Convolutional Neural Network. Github, 26 August 2021. Available online: https:\/\/goodboychan.github.io\/python\/coursera\/tensorflow_probability\/icl\/2021\/08\/26\/01-Bayesian-Convolutional-Neural-Network.html."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.1007\/s10994-017-5646-4","article-title":"Weightless neural networks for open set recognition","volume":"106","author":"Cardoso","year":"2017","journal-title":"Mach. Learn."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Bendale, A., and Boult, T.E. (2016, January 27\u201330). Towards open set deep networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref_20","unstructured":"Kardan, N., and Stanley, K. (2016). Fitted Learning: Models with Awareness of Their Limits, Department of Computer Science, University of Central Florida."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, W., Huang, D., Zhou, M., Lin, J., and Wang, X. (2023). Open-Set Signal Recognition Based on Transformer and Wasserstein Distance. Appl. Sci., 13.","DOI":"10.3390\/app13042151"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3375394","DOI":"10.1155\/2021\/3375394","article-title":"Open Set Sheep Face Recognition Based on Euclidean Space Metric","volume":"2021","author":"Xue","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref_23","unstructured":"Dhamija, A.R., Gunther, M., and Boult, T. (2018, January 2\u20138). Reducing Network Agnostophobia. Proceedings of the 32nd Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2317","DOI":"10.1109\/TPAMI.2014.2321392","article-title":"Probability Models for Open Set Recognition","volume":"36","author":"Scheirer","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108774","DOI":"10.1016\/j.apacoust.2022.108774","article-title":"Open set recognition of underwater acoustic targets based on GRU-CAE collaborative deep learning network","volume":"193","author":"Yang","year":"2022","journal-title":"Appl. Acoust."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"130101","DOI":"10.1016\/j.energy.2023.130101","article-title":"Open set recognition fault diagnosis framework based on convolutional prototype learning network for nuclear power plants","volume":"290","author":"LLi","year":"2024","journal-title":"Energy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7303","DOI":"10.1109\/JSTARS.2023.3299703","article-title":"WildFishNet: Open Set Wild Fish Recognition Deep Neural Network with Fusion Activation Pattern","volume":"16","author":"Zhang","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Pavez, J., and Allende, H. (2024). A Hybrid System Based on Bayesian Networks and Deep Learning for Explainable Mental Health Diagnosis. Appl. Sci., 14.","DOI":"10.3390\/app14188283"},{"key":"ref_29","unstructured":"Graves, A. (2011, January 12\u201315). Practical Variational Inference for Neural Networks. Proceedings of the Conference on Neural Information Processing Systems, Granada, Spain."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1257\/jep.28.2.3","article-title":"Big Data: New Tricks for Econometrics","volume":"28","author":"Varian","year":"2017","journal-title":"J. Econ. Perspect."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","article-title":"Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods","volume":"110","author":"Waegeman","year":"2021","journal-title":"Mach. Learn."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/4\/95\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:11:41Z","timestamp":1760029901000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/4\/95"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":31,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["bdcc9040095"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9040095","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,4,9]]}}}