{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:30:30Z","timestamp":1777609830225,"version":"3.51.4"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2018,4,30]],"date-time":"2018-04-30T00:00:00Z","timestamp":1525046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Security Science and Engineering Faculty Fellowship award numbe"},{"DOI":"10.13039\/100000001","name":"National Science Foundation award numbe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Semiconductor Research Corporation award numbe"},{"name":"Intel Corporation award numbe"},{"name":"Center for Spintronic Materials, Interfaces, and Novel Architectures (CSPIN), a MARCO and DARPA sponsored StarNet center award numbe"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2018,4,30]]},"abstract":"<jats:p>Neural networks, with their remarkable ability to derive meaning from a large volume of complicated or imprecise data, can be used to extract patterns and detect trends that are too complex for the von Neumann computing paradigm. Their considerable computational requirements stretch the capabilities of even modern computing platforms. We propose an approximate multiplier that exploits the inherent application resilience to error and utilizes the notion of computation sharing to achieve improved energy consumption for neural networks. We also propose a Multiplier-less Artificial Neuron (MAN), which is even more compact and energy efficient. We also propose a network retraining methodology to recover some of the accuracy loss due to the use of these approximate multipliers. We evaluated the proposed algorithm\/design on several recognition applications. The results show that we achieve \u223c33%, \u223c32%, and \u223c25% reduction in power consumption and \u223c33%, \u223c34%, and \u223c27% reduction in area, respectively, for 12-, 8-, and 4-bit MAN, with a maximum \u223c2.4% loss in accuracy compared to a conventional neuron implementation of equivalent bit precision. These comparisons were performed under iso-speed conditions.<\/jats:p>","DOI":"10.1145\/3097264","type":"journal-article","created":{"date-parts":[[2018,7,12]],"date-time":"2018-07-12T15:38:47Z","timestamp":1531409927000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":75,"title":["Energy-Efficient Neural Computing with Approximate Multipliers"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0086-1076","authenticated-orcid":false,"given":"Syed Shakib","family":"Sarwar","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swagath","family":"Venkataramani","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aayush","family":"Ankit","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Raghunathan","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0086-1076","authenticated-orcid":false,"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,7,12]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Handwritten Digit Recognition Dataset MNIST. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/.  Handwritten Digit Recognition Dataset MNIST. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"e_1_2_1_2_1","unstructured":"MATLAB Based Neural Network Simulator. Retrieved from https:\/\/github.com\/rasmusbergpalm\/DeepLearnToolbox.  MATLAB Based Neural Network Simulator. Retrieved from https:\/\/github.com\/rasmusbergpalm\/DeepLearnToolbox."},{"key":"e_1_2_1_3_1","unstructured":"C++ Based Neural Network Simulator. Retrieved from https:\/\/github.com\/nyanp\/tiny-cnn.  C++ Based Neural Network Simulator. Retrieved from https:\/\/github.com\/nyanp\/tiny-cnn."},{"key":"e_1_2_1_4_1","first-page":"880","article-title":"Design of approximate multiplier for error-tolerant applications","volume":"3","author":"Anand Shikha","year":"2013","unstructured":"Shikha Anand and Anil Kishore Saxena . 2013 . Design of approximate multiplier for error-tolerant applications . Int. J. Eng. Res. Appl. 3 (2013), 880 -- 883 . Shikha Anand and Anil Kishore Saxena. 2013. Design of approximate multiplier for error-tolerant applications. Int. J. Eng. Res. Appl. 3 (2013), 880--883.","journal-title":"Int. J. Eng. Res. Appl."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.111"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1815993"},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of the Symposium on Operating Systems Design and Implementation (OSDI\u201914)","volume":"14","author":"Chilimbi Trishul M.","year":"2014","unstructured":"Trishul M. Chilimbi , Yutaka Suzue , Johnson Apacible , and Karthik Kalyanaraman . 2014 . Project Adam: Building an efficient and scalable deep learning training system . In Proceedings of the Symposium on Operating Systems Design and Implementation (OSDI\u201914) , Vol. 14 . 571--582. Trishul M. Chilimbi, Yutaka Suzue, Johnson Apacible, and Karthik Kalyanaraman. 2014. Project Adam: Building an efficient and scalable deep learning training system. In Proceedings of the Symposium on Operating Systems Design and Implementation (OSDI\u201914), Vol. 14. 571--582."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1837274.1837411"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2011.2179038"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2009.10.004"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2004.08.011"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.48"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML\u201915)","author":"Gupta Suyog","year":"2015","unstructured":"Suyog Gupta , Ankur Agrawal , Kailash Gopalakrishnan , and Pritish Narayanan . 2015 . Deep learning with limited numerical precision . In Proceedings of the 32nd International Conference on Machine Learning (ICML\u201915) . 1737--1746. Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan. 2015. Deep learning with limited numerical precision. In Proceedings of the 32nd International Conference on Machine Learning (ICML\u201915). 1737--1746."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2016802.2016898"},{"key":"e_1_2_1_16_1","volume-title":"Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv Preprint arXiv:1605.06402","author":"Gysel Philipp","year":"2016","unstructured":"Philipp Gysel . 2016 . Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv Preprint arXiv:1605.06402 (2016). Philipp Gysel. 2016. Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv Preprint arXiv:1605.06402 (2016)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_2_1_20_1","volume-title":"Harris Jr","author":"Hoang Roger V.","year":"2013","unstructured":"Roger V. Hoang , Devyani Tanna , Laurence C. Jayet Bray , Sergiu M. Dascalu , and Frederick C . Harris Jr . 2013 . A novel CPU\/GPU simulation environment for large-scale biologically realistic neural modeling. Front. Neuroinformat . 7 (2013). Roger V. Hoang, Devyani Tanna, Laurence C. Jayet Bray, Sergiu M. Dascalu, and Frederick C. Harris Jr. 2013. A novel CPU\/GPU simulation environment for large-scale biologically realistic neural modeling. Front. Neuroinformat. 7 (2013)."},{"key":"e_1_2_1_21_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50 fewer parameters and &lt;0.5MB model size. arXiv Preprint arXiv:1602.07360","author":"Iandola Forrest N.","year":"2016","unstructured":"Forrest N. Iandola , Song Han , Matthew W. Moskewicz , Khalid Ashraf , William J. Dally , and Kurt Keutzer . 2016. SqueezeNet: AlexNet-level accuracy with 50 fewer parameters and &lt;0.5MB model size. arXiv Preprint arXiv:1602.07360 ( 2016 ). Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50 fewer parameters and &lt;0.5MB model size. arXiv Preprint arXiv:1602.07360 (2016)."},{"key":"e_1_2_1_22_1","volume-title":"Raquel Urtasun, and Andreas Moshovos.","author":"Judd Patrick","year":"2015","unstructured":"Patrick Judd , Jorge Albericio , Tayler Hetherington , Tor Aamodt , Natalie Enright Jerger , Raquel Urtasun, and Andreas Moshovos. 2015 . Reduced-precision strategies for bounded memory in deep neural nets. arXiv Preprint arXiv:1511.05236 (2015). Patrick Judd, Jorge Albericio, Tayler Hetherington, Tor Aamodt, Natalie Enright Jerger, Raquel Urtasun, and Andreas Moshovos. 2015. Reduced-precision strategies for bounded memory in deep neural nets. arXiv Preprint arXiv:1511.05236 (2015)."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366169"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1021\/nl203687n"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2561828.2561854"},{"key":"e_1_2_1_26_1","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. (2009).  Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2015.7273495"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_1_29_1","volume-title":"Network in network. arXiv Preprint arXiv:1312.4400","author":"Lin Min","year":"2013","unstructured":"Min Lin , Qiang Chen , and Shuicheng Yan . 2013. Network in network. arXiv Preprint arXiv:1312.4400 ( 2013 ). Min Lin, Qiang Chen, and Shuicheng Yan. 2013. Network in network. arXiv Preprint arXiv:1312.4400 (2013)."},{"key":"e_1_2_1_30_1","volume-title":"Neural networks with few multiplications. arXiv Preprint arXiv:1510.03009","author":"Lin Zhouhan","year":"2015","unstructured":"Zhouhan Lin , Matthieu Courbariaux , Roland Memisevic , and Yoshua Bengio . 2015. Neural networks with few multiplications. arXiv Preprint arXiv:1510.03009 ( 2015 ). Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, and Yoshua Bengio. 2015. Neural networks with few multiplications. arXiv Preprint arXiv:1510.03009 (2015)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.09.039"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.01.167"},{"key":"e_1_2_1_33_1","volume-title":"Scientists see promise in deep-learning programs. New York Times","author":"Markoff John","year":"2012","unstructured":"John Markoff . 2012. Scientists see promise in deep-learning programs. New York Times ( 2012 ), 11--27. John Markoff. 2012. Scientists see promise in deep-learning programs. New York Times (2012), 11--27."},{"key":"e_1_2_1_34_1","unstructured":"M. J. Miller. 2016. Google\u2019s Tensor Processing Units Change the Rules for Machine Learning. Retrieved from http:\/\/forwardthinking.pcmag.com\/chips\/344686-google-s-tensor-processing-units-change-the-rules-for-machine-learning.  M. J. Miller. 2016. Google\u2019s Tensor Processing Units Change the Rules for Machine Learning. Retrieved from http:\/\/forwardthinking.pcmag.com\/chips\/344686-google-s-tensor-processing-units-change-the-rules-for-machine-learning."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2010.03.021"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the 27th International Conference on Machine Learning (ICML\u201910)","author":"Nair Vinod","unstructured":"Vinod Nair and Geoffrey E. Hinton . 2010. Rectified linear units improve restricted Boltzmann machines . In Proceedings of the 27th International Conference on Machine Learning (ICML\u201910) . 807--814. Vinod Nair and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML\u201910). 807--814."},{"key":"e_1_2_1_39_1","volume-title":"Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning","volume":"2011","author":"Netzer Yuval","unstructured":"Yuval Netzer , Tao Wang , Adam Coates , Alessandro Bissacco , Bo Wu , and Andrew Y. Ng . 2011. Reading digits in natural images with unsupervised feature learning . In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning , Vol. 2011 . 5. Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Vol. 2011. 5."},{"key":"e_1_2_1_40_1","volume-title":"Proceedings of the 28th International Conference on Machine Learning (ICML\u201911)","author":"Ngiam Jiquan","unstructured":"Jiquan Ngiam , Adam Coates , Ahbik Lahiri , Bobby Prochnow , Quoc V. Le , and Andrew Y. Ng . 2011. On optimization methods for deep learning . In Proceedings of the 28th International Conference on Machine Learning (ICML\u201911) . 265--272. Jiquan Ngiam, Adam Coates, Ahbik Lahiri, Bobby Prochnow, Quoc V. Le, and Andrew Y. Ng. 2011. On optimization methods for deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML\u201911). 265--272."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2009.10.016"},{"key":"e_1_2_1_42_1","unstructured":"Rasmus Berg Palm. 2012. Prediction as a candidate for learning deep hierarchical models of data. Technical Universtiy of Denmark 5.  Rasmus Berg Palm. 2012. Prediction as a candidate for learning deep hierarchical models of data. Technical Universtiy of Denmark 5."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862012"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2012.2227969"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/2648668.2648703"},{"key":"e_1_2_1_47_1","volume-title":"Proceedings of the Design, Automation 8 Test in Europe Conference 8 Exhibition (DATE\u201916)","author":"Sarwar Syed Shakib","year":"2016","unstructured":"Syed Shakib Sarwar , Swagath Venkataramani , Anand Raghunathan , and Kaushik Roy . 2016 . Multiplier-less artificial neurons exploiting error resiliency for energy-efficient neural computing . In Proceedings of the Design, Automation 8 Test in Europe Conference 8 Exhibition (DATE\u201916) . IEEE, 145--150. Syed Shakib Sarwar, Swagath Venkataramani, Anand Raghunathan, and Kaushik Roy. 2016. Multiplier-less artificial neurons exploiting error resiliency for energy-efficient neural computing. In Proceedings of the Design, Automation 8 Test in Europe Conference 8 Exhibition (DATE\u201916). IEEE, 145--150."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4914111"},{"key":"e_1_2_1_49_1","volume-title":"Proposal for neuromorphic hardware using spin devices. arXiv Preprint arXiv:1206.3227","author":"Sharad Mrigank","year":"2012","unstructured":"Mrigank Sharad , Charles Augustine , Georgios Panagopoulos , and Kaushik Roy . 2012. Proposal for neuromorphic hardware using spin devices. arXiv Preprint arXiv:1206.3227 ( 2012 ). Mrigank Sharad, Charles Augustine, Georgios Panagopoulos, and Kaushik Roy. 2012. Proposal for neuromorphic hardware using spin devices. arXiv Preprint arXiv:1206.3227 (2012)."},{"key":"e_1_2_1_50_1","first-page":"979","article-title":"Low power floating point computation sharing multiplier for signal processing applications","volume":"5","author":"Sivanantham S.","year":"2013","unstructured":"S. Sivanantham , K. Jagannadha Naidu , S. Balamurugan , and D. Bhuvana Phaneendra . 2013 . Low power floating point computation sharing multiplier for signal processing applications . Int. J. Eng. Technol. 5 , 2 (2013), 979 -- 985 . S. Sivanantham, K. Jagannadha Naidu, S. Balamurugan, and D. Bhuvana Phaneendra. 2013. Low power floating point computation sharing multiplier for signal processing applications. Int. J. Eng. Technol. 5, 2 (2013), 979--85.","journal-title":"Int. J. Eng. Technol."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2133210"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2011.6131488"},{"key":"e_1_2_1_53_1","volume-title":"A New Benchmark Dataset for Handwritten Character Recognition","author":"der Maaten Laurens Van","unstructured":"Laurens Van der Maaten . 2009. A New Benchmark Dataset for Handwritten Character Recognition . Tilburg University , The Netherlands , , 2--5. Laurens Van der Maaten. 2009. A New Benchmark Dataset for Handwritten Character Recognition. Tilburg University, The Netherlands, , 2--5."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627613"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228504"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.201202383"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/2485288.2485341"}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097264","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097264","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:30:38Z","timestamp":1750217438000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097264"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,30]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,4,30]]}},"alternative-id":["10.1145\/3097264"],"URL":"https:\/\/doi.org\/10.1145\/3097264","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"value":"1550-4832","type":"print"},{"value":"1550-4840","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,30]]},"assertion":[{"value":"2017-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-07-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}