{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:39:07Z","timestamp":1779385147553,"version":"3.53.1"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2018,10,31]],"date-time":"2018-10-31T00:00:00Z","timestamp":1540944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2018,10,31]]},"abstract":"<jats:p>Cellular neural networks (CeNNs) have been widely adopted in image processing tasks. Recently, various hardware implementations of CeNNs have emerged in the literature, with Field Programmable Gate Array (FPGA) being one of the most popular choices due to its high flexibility and low time-to-market. However, CeNNs typically involve extensive computations in a recursive manner. As an example, to simply process an image of 1,920 \u00d7 1,080 pixels requires 4--8 Giga floating point multiplications (for 3 \u00d7 3 templates and 50\u2013100 iterations), which needs to be done in a timely manner for real-time applications. To address this issue, in this article, we propose a compressed CeNN framework for efficient FPGA implementations. It involves various techniques, such as incremental quantization and early exit, which significantly reduces computation demands while maintaining an acceptable performance. Particularly, incremental quantization quantizes the numbers in CeNN templates to powers of two, so that complex and expensive multiplications can be converted to simple and cheap shift operations, which only require a minimum number of registers and logical elements (LEs). While a similar concept has been explored in hardware implementations of Convolutional Neural Networks (CNNs), CeNNs have completely different computation patterns, which require different quantization and implementation strategies. Experimental results on FPGAs show that incremental quantization and early exit can achieve a speedup of up to 7.8\u00d7 and 8.3\u00d7, respectively, compared with the state-of-the-art implementations, while with almost no performance loss with four widely adopted applications. We also discover that different from CNNs, the optimal quantization strategies of CeNNs depend heavily on the applications. We hope that our work can serve as a pioneer in the hardware optimization of CeNNs.<\/jats:p>","DOI":"10.1145\/3264817","type":"journal-article","created":{"date-parts":[[2018,12,4]],"date-time":"2018-12-04T13:14:12Z","timestamp":1543929252000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Efficient Hardware Implementation of Cellular Neural Networks with Incremental Quantization and Early Exit"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1046-6379","authenticated-orcid":false,"given":"Xiaowei","family":"Xu","sequence":"first","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianchen","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Hu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinglan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyu","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,12]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10470-013-0192-x"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2005.08.067"},{"key":"e_1_2_1_3_1","volume-title":"Chua and Tamas Roska","author":"Leon","year":"2002","unstructured":"Leon O. Chua and Tamas Roska . 2002 . Cellular Neural Networks and Visual Computing: Foundations and Applications. Cambridge University Press . Leon O. Chua and Tamas Roska. 2002. Cellular Neural Networks and Visual Computing: Foundations and Applications. Cambridge University Press."},{"key":"e_1_2_1_4_1","unstructured":"Matthieu Courbariaux Itay Hubara Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or &minus;1. arXiv Preprint arXiv:1602.02830.  Matthieu Courbariaux Itay Hubara Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or &minus;1. arXiv Preprint arXiv:1602.02830."},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE\u201914)","author":"Duraisamy M.","unstructured":"M. Duraisamy and F. Mary Magdalene Jane. 2014. Cellular neural network based medical image segmentation using artificial bee colony algorithm . In Proceedings of the International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE\u201914) . IEEE, 1--6. M. Duraisamy and F. Mary Magdalene Jane. 2014. Cellular neural network based medical image segmentation using artificial bee colony algorithm. In Proceedings of the International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE\u201914). IEEE, 1--6."},{"key":"e_1_2_1_6_1","first-page":"9","article-title":"Edge detection in satellite image using cellular neural network","volume":"8","author":"Gazi Osama Basil","year":"2014","unstructured":"Osama Basil Gazi , Mohamed Belal , and Hala Abdel-Galil . 2014 . Edge detection in satellite image using cellular neural network . System 8 (2014), 9 . Osama Basil Gazi, Mohamed Belal, and Hala Abdel-Galil. 2014. Edge detection in satellite image using cellular neural network. System 8 (2014), 9.","journal-title":"System"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/cta.4490200503"},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201994)","volume":"4","author":"Harrer Hubert","unstructured":"Hubert Harrer , Josef A. Nossek , Tams Roska , and Leon O. Chua . 1994. A current-msode DTCNN universal chip . In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201994) , Vol. 4 . IEEE, 135--138. Hubert Harrer, Josef A. Nossek, Tams Roska, and Leon O. Chua. 1994. A current-msode DTCNN universal chip. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201994), Vol. 4. IEEE, 135--138."},{"key":"e_1_2_1_9_1","first-page":"3","article-title":"Cellular neural network-based thermal modelling for real-time robotic path planning","volume":"7","author":"Hills Jeremy","year":"2014","unstructured":"Jeremy Hills and Yongmin Zhong . 2014 . Cellular neural network-based thermal modelling for real-time robotic path planning . Int. J. Agile Syst. Manage. 7 , 3 -- 4 (2014), 261--281. Jeremy Hills and Yongmin Zhong. 2014. Cellular neural network-based thermal modelling for real-time robotic path planning. Int. J. Agile Syst. Manage. 7, 3--4 (2014), 261--281.","journal-title":"Int. J. Agile Syst. Manage."},{"key":"e_1_2_1_10_1","unstructured":"Hlevkin. 2017. Retrieved from http:\/\/www.hlevkin.com\/06testimages.htm.  Hlevkin. 2017. Retrieved from http:\/\/www.hlevkin.com\/06testimages.htm."},{"key":"e_1_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems","author":"Hubara Itay","unstructured":"Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , and Yoshua Bengio . 2016. Binarized neural networks . In Advances in Neural Information Processing Systems . Springer , 4107--4115. Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks. In Advances in Neural Information Processing Systems. Springer, 4107--4115."},{"key":"e_1_2_1_12_1","unstructured":"K. Karacs G. Y. Cserey Zarndy P. Szolgay C. S. Rekeczky L. Kek V. Szab G. Pazienza and T. Roska. 2007. Software library for cellular wave computing engines. Cellular Wave Computing Library (Templates Algorithms and Programs) L. K\u00e9k K. Karacs and T. Roska (Eds.). Retrieved from http:\/\/cnn-technology.itk.ppke.hu\/Library_v2.1b.pdf.  K. Karacs G. Y. Cserey Zarndy P. Szolgay C. S. Rekeczky L. Kek V. Szab G. Pazienza and T. Roska. 2007. Software library for cellular wave computing engines. Cellular Wave Computing Library (Templates Algorithms and Programs) L. K\u00e9k K. Karacs and T. Roska (Eds.). Retrieved from http:\/\/cnn-technology.itk.ppke.hu\/Library_v2.1b.pdf."},{"key":"e_1_2_1_13_1","volume-title":"Encyclopedia of Machine Learning","author":"Kennedy James","unstructured":"James Kennedy . 2011. Particle swarm optimization . In Encyclopedia of Machine Learning . Springer , 760--766. James Kennedy. 2011. Particle swarm optimization. In Encyclopedia of Machine Learning. Springer, 760--766."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2085443"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2010.12.017"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.121"},{"key":"e_1_2_1_17_1","volume-title":"Cellular Neural Networks: Chaos, Complexity and VLSI Processing","author":"Manganaro Gabriele","unstructured":"Gabriele Manganaro , Paolo Arena , and Luigi Fortuna . 2012. Cellular Neural Networks: Chaos, Complexity and VLSI Processing , Vol. 1 . Springer Science 8 Business Media. Gabriele Manganaro, Paolo Arena, and Luigi Fortuna. 2012. Cellular Neural Networks: Chaos, Complexity and VLSI Processing, Vol. 1. Springer Science 8 Business Media."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.09.029"},{"key":"e_1_2_1_19_1","volume-title":"An improved cellular nonlinear network architecture for binary and greyscale image processing","author":"Muller Jens","year":"2016","unstructured":"Jens Muller , Robert Wittig , Jan Muller , and Ronald Tetzlaff . 2016. An improved cellular nonlinear network architecture for binary and greyscale image processing . IEEE Trans. Circ. Syst . II : Express Briefs ( 2016 ). Jens Muller, Robert Wittig, Jan Muller, and Ronald Tetzlaff. 2016. An improved cellular nonlinear network architecture for binary and greyscale image processing. IEEE Trans. Circ. Syst. II: Express Briefs (2016)."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2006.02.016"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/INDS.2011.6024781"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2004.827621"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.09.020"},{"key":"e_1_2_1_25_1","volume-title":"Proceedings of the 4th International Conference on Learning Representations.","author":"Song Han","unstructured":"Han Song , Pool Jeff , Tran John , and William J. Dally . 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding . In Proceedings of the 4th International Conference on Learning Representations. Han Song, Pool Jeff, Tran John, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In Proceedings of the 4th International Conference on Learning Representations."},{"key":"e_1_2_1_26_1","volume-title":"Exerpta Medica. International Congress Series","volume":"1069","author":"Suckling John","unstructured":"John Suckling , J. Parker , D. Dance , S. Astley , I. Hutt , C. Boggis , I. Ricketts , E. Stamatakis , N. Cerneaz , S. Kok et al. 1994. The mammographic image analysis society digital mammogram database . In Exerpta Medica. International Congress Series , Vol. 1069 . 375--378. John Suckling, J. Parker, D. Dance, S. Astley, I. Hutt, C. Boggis, I. Ricketts, E. Stamatakis, N. Cerneaz, S. Kok et al. 1994. The mammographic image analysis society digital mammogram database. In Exerpta Medica. International Congress Series, Vol. 1069. 375--378."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1997.0646"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950419"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-018-0059-3"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2729344"},{"key":"e_1_2_1_33_1","volume-title":"MDA: A reconfigurable memristor-based distance accelerator for time series mining on data centers","author":"Xu Xiaowei","year":"2018","unstructured":"Xiaowei Xu , Feng Lin , Wenyao Xu , Xinwei Yao , Yiyu Shi , Dewen Zeng , and Yu Hu . 2018 . MDA: A reconfigurable memristor-based distance accelerator for time series mining on data centers . IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ( 2018). Xiaowei Xu, Feng Lin, Wenyao Xu, Xinwei Yao, Yiyu Shi, Dewen Zeng, and Yu Hu. 2018. MDA: A reconfigurable memristor-based distance accelerator for time series mining on data centers. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2018)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183584.3183611"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3199700.3199821"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00866"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062200"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2014.2345502"},{"key":"e_1_2_1_39_1","volume-title":"Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA\u201916)","author":"Yildiz Nerhun","year":"2016","unstructured":"Nerhun Yildiz , Evren Cesur , and Vedat Tavsanoglu . 2016 . On the way to a third-generation real-time cellular neural network processor . In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA\u201916) . Nerhun Yildiz, Evren Cesur, and Vedat Tavsanoglu. 2016. On the way to a third-generation real-time cellular neural network processor. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA\u201916)."},{"key":"e_1_2_1_40_1","volume-title":"Proceedings of the 5th International Conference on Learning Representations.","author":"Zhou Aojun","year":"2017","unstructured":"Aojun Zhou , Anbang Yao , Yiwen Guo , Lin Xu , and Yurong Chen . 2017 . Incremental network quantization: Toward lossless CNNs with low-precision weights . In Proceedings of the 5th International Conference on Learning Representations. Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, and Yurong Chen. 2017. Incremental network quantization: Toward lossless CNNs with low-precision weights. In Proceedings of the 5th International Conference on Learning Representations."}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3264817","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3264817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:07:58Z","timestamp":1750212478000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3264817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,31]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,10,31]]}},"alternative-id":["10.1145\/3264817"],"URL":"https:\/\/doi.org\/10.1145\/3264817","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"value":"1550-4832","type":"print"},{"value":"1550-4840","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,31]]},"assertion":[{"value":"2017-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-12-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}