{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T14:36:38Z","timestamp":1764945398503,"version":"3.46.0"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>In the realm of cyber-physical systems, where tight integration between computational and physical elements is paramount, the demand for efficient and scalable machine learning models is ever-present. Bayesian Neural Networks (BNNs) present a promising avenue for tackling complex tasks in such systems, yet their widespread adoption is hindered by computational complexity and resource constraints. To address these challenges, we propose an energy-efficient FPGA implementation of Probabilistic Bayesian Neural Networks (ProbBNNs), a novel architecture that leverages probabilistic computing principles to streamline inference in BNNs. In ProbBNN, instead of representing each parameter as a random variable with a mean and variance, a set of parameters for each neuron is represented by a Probability Density Function (PDF) that characterizes the distribution of these random variables, with random streams following the PDFs processed through probabilistic computing principles to propagate uncertainty throughout the network. The adoption of probabilistic computing eliminates the need for expensive Multiply-Accumulate (MAC) operations, further enhancing the scalability and cost-effectiveness of our proposed implementation of ProbBNN in real-world applications. Furthermore, Gaussian Mixture Models (GMMs) are employed to efficiently capture the underlying distributions of weights, thereby reducing the number of BNN parameters. Through evaluation and comparison with traditional BNN architectures, this implementation demonstrates significant improvements in computational efficiency, memory utilization, and energy efficiency, making it well suited for deployment in resource-constrained cyber-physical systems, where efficient and reliable decision-making is crucial.<\/jats:p>","DOI":"10.1145\/3748651","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T19:53:08Z","timestamp":1752522788000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Energy-Efficient Probabilistic Bayesian Neural Networks for Resource-Constrained Environments"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9165-5477","authenticated-orcid":false,"given":"Md","family":"Ishak","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Wayne State University, Detroit, Michigan, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7491-0440","authenticated-orcid":false,"given":"Mohammed","family":"Alawad","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Wayne State University, Detroit, Michigan, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"issue":"7553","key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/nature14541","article-title":"Probabilistic machine learning and artificial intelligence","volume":"512","author":"Ghahramani Z.","year":"2015","unstructured":"Z. Ghahramani. 2015. Probabilistic machine learning and artificial intelligence. Nature 512, 7553 (2015), 452\u2013459.","journal-title":"Nature"},{"key":"e_1_3_1_3_2","doi-asserted-by":"crossref","first-page":"18910","DOI":"10.1109\/ACCESS.2023.3247947","article-title":"A Bayesian deep learning approach with convolutional feature engineering to discriminate cyber-physical intrusions in smart grid systems","volume":"11","author":"Kaur D.","year":"2023","unstructured":"D. Kaur, A. Anwar, I. Kamwa, S. Islam, S. M. Muyeen, and N. Hosseinzadeh. 2023. A Bayesian deep learning approach with convolutional feature engineering to discriminate cyber-physical intrusions in smart grid systems. IEEE Access 11 (2023), 18910\u201318920.","journal-title":"IEEE Access"},{"issue":"2","key":"e_1_3_1_4_2","article-title":"Cyber physical system for distributed network using DoS based hierarchical Bayesian network","volume":"21","author":"Ma X.","year":"2023","unstructured":"X. Ma, L. Almutairi, A. M. Alwakeel, and M. H. Alhameed. 2023. Cyber physical system for distributed network using DoS based hierarchical Bayesian network. Journal of Grid Computing 21, 2 (2023), 27.","journal-title":"Journal of Grid Computing"},{"key":"e_1_3_1_5_2","first-page":"5574","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Kendall A.","year":"2017","unstructured":"A. Kendall and Y. Gal. 2017. What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems (NIPS) 30 (2017), 5574\u20135584."},{"key":"e_1_3_1_6_2","first-page":"118","volume-title":"Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence","author":"Tassi C.","year":"2019","unstructured":"C. Tassi. 2019. Bayesian convolutional neural network: Robustly quantify uncertainty for misclassifications detection. In Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence. Springer International Publishing, 118\u2013132."},{"issue":"4","key":"e_1_3_1_7_2","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1080\/15472450.2015.1082428","article-title":"Interpretation of bayesian neural networks for predicting the duration of detected incidents","volume":"20","author":"Park H.","year":"2016","unstructured":"H. Park, A. Haghani, and X. Zhang. 2016. Interpretation of bayesian neural networks for predicting the duration of detected incidents. Journal of Intelligent Transportation Systems 20, 4 (2016), 385\u2013400.","journal-title":"Journal of Intelligent Transportation Systems"},{"issue":"4","key":"e_1_3_1_8_2","first-page":"980","article-title":"CiM-BNN:Computing-in-MRAM architecture for stochastic computing based Bayesian neural network","volume":"12","author":"Gu Huiyi","year":"2023","unstructured":"Huiyi Gu, Xiaotao Jia, Yuhao Liu, Jianlei Yang, Xueyan Wang, Youguang Zhang, Sorin Dan Cotofana, and Weisheng Zhao. 2023. CiM-BNN:Computing-in-MRAM architecture for stochastic computing based Bayesian neural network. IEEE Transactions on Emerging Topics in Computing 12, 4 (2023), 980\u2013990.","journal-title":"IEEE Transactions on Emerging Topics in Computing"},{"doi-asserted-by":"publisher","key":"e_1_3_1_9_2","DOI":"10.1109\/TNNLS.2023.3265533"},{"key":"e_1_3_1_10_2","first-page":"1402","article-title":"BYNQNet: Bayesian neural network with quadratic activations for sampling-free uncertainty estimation on FPGA","author":"Awano H.","year":"2020","unstructured":"H. Awano and M. Hashimoto. 2020. BYNQNet: Bayesian neural network with quadratic activations for sampling-free uncertainty estimation on FPGA. In Proceedings of the IEEE\/ACM Design, Automation and Test in Europe Conference and Exhibition (DATE), 1402\u20131407.","journal-title":"Proceedings of the IEEE\/ACM Design, Automation and Test in Europe Conference and Exhibition (DATE)"},{"doi-asserted-by":"publisher","key":"e_1_3_1_11_2","DOI":"10.1016\/j.vlsi.2022.11.005"},{"issue":"4","key":"e_1_3_1_12_2","first-page":"1703","article-title":"Efficient computation reduction in Bayesian neural networks through feature decomposition and memorization","volume":"32","author":"Jia Xiaotao","year":"2020","unstructured":"Xiaotao Jia, Jianlei Yang, Runze Liu, Xueyan Wang, Sorin Dan Cotofana, and Weisheng Zhao. 2020. Efficient computation reduction in Bayesian neural networks through feature decomposition and memorization. IEEE Transactions on Natural Network Learning Systems 32, 4 (2020), 1703\u20131712.","journal-title":"IEEE Transactions on Natural Network Learning Systems"},{"key":"e_1_3_1_13_2","first-page":"229","volume-title":"Proceedings of the 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Wan Q.","year":"2020","unstructured":"Q. Wan and X. Fu. 2020. Fast-BCNN: Massive neuron skipping in Bayesian convolutional neural networks. In Proceedings of the 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), 229\u2013240."},{"doi-asserted-by":"publisher","key":"e_1_3_1_14_2","DOI":"10.1109\/TCAD.2022.3160948"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/A-SSCC56115.2022.9980539","volume-title":"Proceedings of the 2022 IEEE Asian Solid-State Circuits Conference (A-SSCC)","author":"Dorrance Richard","year":"2022","unstructured":"Richard Dorrance, Deepak Dasalukunte, Hechen Wang, Renzhi Liu, and Brent Carlton. 2022. Energy efficient BNN accelerator using CiM and a time-interleaved Hadamard digital GRNG in 22nm CMOS. In Proceedings of the 2022 IEEE Asian Solid-State Circuits Conference (A-SSCC), 2\u20134."},{"key":"e_1_3_1_16_2","first-page":"724","volume-title":"Proceedings of the Great Lakes Symposium on VLSI (GLSVLSI)","author":"Ishak M.","year":"2024","unstructured":"M. Ishak and M. Alawad. 2024. Probabilistic Bayesian neural networks for efficient inference. In Proceedings of the Great Lakes Symposium on VLSI (GLSVLSI), 724\u2013729."},{"doi-asserted-by":"publisher","key":"e_1_3_1_17_2","DOI":"10.1109\/TETC.2016.2601220"},{"doi-asserted-by":"publisher","key":"e_1_3_1_18_2","DOI":"10.1109\/TMSCS.2018.2886266"},{"key":"e_1_3_1_19_2","first-page":"827","volume-title":"Encyclopedia of Biometrics","author":"Reynolds D.","unstructured":"D. Reynolds. 2015. Gaussian mixture models. In Encyclopedia of Biometrics. Stan Z. Li and Anil K. Jain (Eds.), Springer, Boston, MA, 827\u2013832."},{"unstructured":"A. Foong D. Burt Y. Li and R. Turner. 2020. On the expressiveness of approximate inference in Bayesian neural networks. arXiv:1909.00719. Retrieved from https:\/\/arxiv.org\/abs\/1909.00719","key":"e_1_3_1_20_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_21_2","DOI":"10.1016\/S1573-4412(01)05010-3"},{"unstructured":"K. Shridhar F. Laumann and M. Liwicki. 2019. A comprehensive guide to Bayesian convolutional neural network with variational inference. arXiv:1901.02731. Retrieved from https:\/\/arxiv.org\/abs\/1901.02731","key":"e_1_3_1_22_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_23_2","DOI":"10.1038\/s41598-017-17876-z"},{"doi-asserted-by":"publisher","key":"e_1_3_1_24_2","DOI":"10.3847\/1538-3881\/ab2390"},{"doi-asserted-by":"publisher","key":"e_1_3_1_25_2","DOI":"10.1023\/a:1011141724916"},{"key":"e_1_3_1_26_2","first-page":"3266","volume-title":"Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC)","author":"Feng D.","year":"2018","unstructured":"D. Feng, L. Rosenbaum, and K. Dietmayer. 2018. Towards safe autonomous driving: Capture uncertainty in the deep neural network for lidar 3d vehicle detection. In Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC), 3266\u20133273."},{"unstructured":"Y. Gal and Z. Ghahramani. 2015. Bayesian convolutional neural net-works with Bernoulli approximate variational inference. arXiv:1506.02158. Retrieved from https:\/\/arxiv.org\/abs\/1506.02158","key":"e_1_3_1_27_2"},{"key":"e_1_3_1_28_2","first-page":"29","volume-title":"IEEE Computational Intelligence Magazine","volume":"17","author":"Jospin L. V.","year":"2022","unstructured":"L. V. Jospin, H. Laga, F. Boussaid, W. Buntine, and M. Bennamoun. 2022. Hands-on Bayesian neural networks\u2014A tutorial for deep learning users. IEEE Computational Intelligence Magazine 17, 2 (2022), 29\u201348."},{"doi-asserted-by":"publisher","key":"e_1_3_1_29_2","DOI":"10.1007\/978-1-4899-5841-9_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_30_2","DOI":"10.1109\/TCAD.2019.2897631"},{"doi-asserted-by":"publisher","key":"e_1_3_1_31_2","DOI":"10.1109\/TCAD.2018.2852752"},{"unstructured":"Y. LeCun and C. Burges. 2010. MNIST Handwritten Digit Database. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist","key":"e_1_3_1_32_2"},{"unstructured":"H. Xiao K. Rasul and R. Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747. Retrieved from https:\/\/arxiv.org\/abs\/1708.07747","key":"e_1_3_1_33_2"},{"unstructured":"D. Tran M. Hoffman R. Saurous E. Brevdo K. Murphy and D. Blei. 2017. Deep probabilistic programming. arXiv:1701.03757. Retrieved from https:\/\/arxiv.org\/abs\/1701.03757","key":"e_1_3_1_34_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_35_2","DOI":"10.1109\/5.726791"},{"key":"e_1_3_1_36_2","first-page":"225","volume-title":"Proceedings of the 5th International Conference on Circuits and Systems (ICCS)","author":"Gu H.","year":"2023","unstructured":"H. Gu, X. Jia, Y. Liu, and Y. Zhang. 2023. Enabling efficient Bayesian convolutional neural network with feature pre-extraction and pre-pooling strategies. In Proceedings of the 5th International Conference on Circuits and Systems (ICCS). IEEE, 225\u2013230."},{"doi-asserted-by":"publisher","key":"e_1_3_1_37_2","DOI":"10.1145\/3296957.3173212"}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T14:33:27Z","timestamp":1764945207000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748651"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,5]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3748651"],"URL":"https:\/\/doi.org\/10.1145\/3748651","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"type":"print","value":"1550-4832"},{"type":"electronic","value":"1550-4840"}],"subject":[],"published":{"date-parts":[[2025,12,5]]},"assertion":[{"value":"2024-04-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}