{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:39:26Z","timestamp":1740145166248,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,1,4]],"date-time":"2020-01-04T00:00:00Z","timestamp":1578096000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,4]],"date-time":"2020-01-04T00:00:00Z","timestamp":1578096000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Conacyt","award":["434864"],"award-info":[{"award-number":["434864"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s11554-019-00938-y","type":"journal-article","created":{"date-parts":[[2020,1,4]],"date-time":"2020-01-04T11:03:04Z","timestamp":1578135784000},"page":"1715-1733","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A streaming architecture for Convolutional Neural Networks based on layer operations chaining"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0198-274X","authenticated-orcid":false,"given":"Mois\u00e9s","family":"Arredondo-Vel\u00e1zquez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Diaz-Carmona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cesar","family":"Torres-Huitzil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfredo","family":"Padilla-Medina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Prado-Olivarez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,4]]},"reference":[{"issue":"7553","key":"938_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"938_CR2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"938_CR3","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 1 (2012)"},{"key":"938_CR4","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. European conference on computer vision, pp.\u00a0818\u2013833, Springer, (2014)"},{"key":"938_CR5","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a01\u20139, (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"938_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a0770\u2013778, (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"938_CR7","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp.\u00a07132\u20137141, 2018"},{"key":"938_CR8","doi-asserted-by":"crossref","unstructured":"Sze, V., Chen, Y-H., Yang, T-J., Emer, J.: Efficient processing of deep neural networks: A tutorial and survey. arXiv preprint arXiv:1703.09039 (2017)","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"938_CR9","unstructured":"Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851 (2013)"},{"key":"938_CR10","unstructured":"Dubout, C., Fleuret, F.: Exact acceleration of linear object detectors. European Conference on Computer Vision, pp.\u00a0301\u2013311, Springer, (2012)"},{"key":"938_CR11","series-title":"CBMS-NSF Regional Conference Series in Applied Mathematics","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970364","volume-title":"Arithmetic Complexity of Computations","author":"S Winograd","year":"1980","unstructured":"Winograd, S.: Arithmetic Complexity of Computations. CBMS-NSF Regional Conference Series in Applied Mathematics, vol. 33. Society for Industrial and Applied Mathematics, Philadelphia (1980)"},{"key":"938_CR12","unstructured":"Lu, L., Liang, Y., Xiao, Q., Yan, S.: Evaluating fast algorithms for convolutional neural networks on fpgas. Field-Programmable Custom Computing Machines (FCCM), 2017 IEEE 25th Annual International Symposium on, pp.\u00a0101\u2013108, IEEE, (2017)"},{"key":"938_CR13","unstructured":"Suda, N., Chandra, V., Dasika, G., Mohanty, A., Ma, Y., Vrudhula, S., Seo, J.-s., Cao, Y.: Throughput-optimized opencl-based fpga accelerator for large-scale convolutional neural networks. Proceedings of the 2016 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp.\u00a016\u201325, ACM, (2016)"},{"key":"938_CR14","unstructured":"Zhang, C., Fang, Z., Zhou, P., Pan, P., Cong, J.: Caffeine: towards uniformed representation and acceleration for deep convolutional neural networks. Computer-Aided Design (ICCAD), 2016 IEEE\/ACM International Conference on, pp.\u00a01\u20138, IEEE, (2016)"},{"key":"938_CR15","unstructured":"Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., Song, S. et\u00a0al.: Going deeper with embedded fpga platform for convolutional neural network. Proceedings of the 2016 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp.\u00a026\u201335, ACM, (2016)"},{"issue":"1","key":"938_CR16","doi-asserted-by":"publisher","first-page":"20161134","DOI":"10.1587\/elex.13.20161134","volume":"14","author":"J Chang","year":"2017","unstructured":"Chang, J., Sha, J.: An efficient implementation of 2d convolution in cnn. IEICE Electron. Express 14(1), 20161134\u201320161134 (2017)","journal-title":"IEICE Electron. Express"},{"issue":"5","key":"938_CR17","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1109\/18.532878","volume":"42","author":"GJ Sullivan","year":"1996","unstructured":"Sullivan, G.J.: Efficient scalar quantization of exponential and laplacian random variables. IEEE Trans. Inf. Theor. 42(5), 1365\u20131374 (1996)","journal-title":"IEEE Trans. Inf. Theor."},{"key":"938_CR18","unstructured":"Denil, M., Shakibi, B., Dinh, L., de Freitas, N. et\u00a0al.: Predicting parameters in deep learning. In: Proceedings of the 26th International Conference on Neural Information Processing Systems, vol. 2 (2013)"},{"key":"938_CR19","unstructured":"Gong, Y., Liu, L., Yang, M., Bourdev, L.: Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)"},{"key":"938_CR20","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 7\u201312 December 2015, Montreal, Quebec (2015). http:\/\/papers.nips.cc\/paper\/5784-learning-both-weights-and-connections-for-efficient-neural-network"},{"key":"938_CR21","unstructured":"Hu, H., Peng, R., Tai, Y-W., Tang, C-K.: Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 (2016)"},{"key":"938_CR22","unstructured":"Liu, B., Wang, M., Foroosh, H., Tappen, M., Pensky, M.: Sparse convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a0806\u2013814, (2015)"},{"key":"938_CR23","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 2074\u20132082. Curran Associates, Inc. (2016). http:\/\/papers.nips.cc\/paper\/6504-learning-structured-sparsity-in-deep-neural-networks.pdf"},{"key":"938_CR24","unstructured":"Chen, W., Wilson, J., Tyree, S., Weinberger, K., Chen, Y.: Compressing neural networks with the hashing trick. International Conference on Machine Learning, pp.\u00a02285\u20132294, (2015)"},{"key":"938_CR25","unstructured":"Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., Cong, J.: Optimizing fpga-based accelerator design for deep convolutional neural networks. Proceedings of the 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp.\u00a0161\u2013170, ACM, (2015)"},{"key":"938_CR26","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1145\/2644865.2541967","volume":"49","author":"T Chen","year":"2014","unstructured":"Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., Temam, O.: Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. ACM Sigplan Not. 49, 269\u2013284 (2014). (ACM)","journal-title":"ACM Sigplan Not."},{"issue":"1","key":"938_CR27","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"Y-H Chen","year":"2017","unstructured":"Chen, Y.-H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J.Solid State Circ. 52(1), 127\u2013138 (2017)","journal-title":"IEEE J.Solid State Circ."},{"key":"938_CR28","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/LES.2017.2743247","volume":"9","author":"K Abdelouahab","year":"2017","unstructured":"Abdelouahab, K., Pelcat, M., S\u00e9rot, J., Bourrasset, C., Berry, F.: Tactics to directly map cnn graphs on embedded fpgas. IEEE Embed. Syst. Lett. 9, 113\u2013116 (2017)","journal-title":"IEEE Embed. Syst. Lett."},{"key":"938_CR29","doi-asserted-by":"crossref","unstructured":"Dundar, A., Jin, J., Martini, B., Culurciello, E.: Embedded streaming deep neural networks accelerator with applications. IEEE transactions on neural networks and learning systems, (2017)","DOI":"10.1109\/TNNLS.2016.2545298"},{"key":"938_CR30","unstructured":"Nakahara, H., Sasao, T.: A deep convolutional neural network based on nested residue number system. Field Programmable Logic and Applications (FPL), 2015 25th International Conference on, pp.\u00a01\u20136, IEEE, (2015)"},{"issue":"1","key":"938_CR31","first-page":"198","volume":"65","author":"L Du","year":"2018","unstructured":"Du, L., Du, Y., Li, Y., Su, J., Kuan, Y.-C., Liu, C.-C., Chang, M.-C.F.: A reconfigurable streaming deep convolutional neural network accelerator for internet of things. IEEE Trans. Circ. Syst. 65(1), 198\u2013208 (2018)","journal-title":"IEEE Trans. Circ. Syst."},{"key":"938_CR32","unstructured":"Song, L., Wang, Y., Han, Y., Zhao, X., Liu, B., Li, X.: C-brain: a deep learning accelerator that tames the diversity of cnns through adaptive data-level parallelization. Design Automation Conference (DAC), 2016 53nd ACM\/EDAC\/IEEE, pp.\u00a01\u20136, IEEE, (2016)"},{"key":"938_CR33","doi-asserted-by":"publisher","first-page":"2220","DOI":"10.1109\/TVLSI.2017.2688340","volume":"25","author":"F Tu","year":"2017","unstructured":"Tu, F., Yin, S., Ouyang, P., Tang, S., Liu, L., Wei, S.: Deep convolutional neural network architecture with reconfigurable computation patterns. IEEE Trans. Very Larg. Scale Integr. Syst. 25, 2220\u20132233 (2017). (VLSI)","journal-title":"IEEE Trans. Very Larg. Scale Integr. Syst."},{"issue":"3","key":"938_CR34","first-page":"17","volume":"10","author":"Z Liu","year":"2017","unstructured":"Liu, Z., Dou, Y., Jiang, J., Xu, J., Li, S., Zhou, Y., Xu, Y.: Throughput-optimized fpga accelerator for deep convolutional neural networks. ACM Trans. Reconfigurable Technol. Syst. (TRETS) 10(3), 17 (2017)","journal-title":"ACM Trans. Reconfigurable Technol. Syst. (TRETS)"},{"key":"938_CR35","unstructured":"Li, H., Fan, X., Jiao, L., Cao, W., Zhou, X., Wang, L.: A high performance fpga-based accelerator for large-scale convolutional neural networks. Field Programmable Logic and Applications (FPL), 2016 26th International Conference on, pp.\u00a01\u20139, IEEE, (2016)"},{"key":"938_CR36","unstructured":"Li, N., Takaki, S., Tomiokay, Y., Kitazawa, H.: A multistage dataflow implementation of a deep convolutional neural network based on fpga for high-speed object recognition. Image Analysis and Interpretation (SSIAI), 2016 IEEE Southwest Symposium on, pp.\u00a0165\u2013168, IEEE, (2016)"},{"key":"938_CR37","unstructured":"Lacey, G., Taylor, G.W., Areibi, S.: Deep learning on fpgas: Past, present, and future. CoRR. arxiv:abs\/1602.04283 (2016)"},{"key":"938_CR38","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1145\/1816038.1815993","volume":"38","author":"S Chakradhar","year":"2010","unstructured":"Chakradhar, S., Sankaradas, M., Jakkula, V., Cadambi, S.: A dynamically configurable coprocessor for convolutional neural networks. ACM SIGARCH Comput. Archit. News 38, 247\u2013257 (2010). (ACM)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"938_CR39","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. Proceedings of COMPSTAT\u20192010, pp.\u00a0177\u2013186, Springer, (2010)"},{"key":"938_CR40","unstructured":"Fu, Y., Wu, E., Sirasao, A., Attia, S., Khan, K., Wittig, R.: Deep learning with int8 optimization on xilinx devices. White paper of Xilinx (2016)"},{"key":"938_CR41","unstructured":"Gysel, P.: Ristretto: Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:1605.06402 (2016)"},{"issue":"11","key":"938_CR42","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-019-00938-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11554-019-00938-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-019-00938-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T00:34:55Z","timestamp":1609634095000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11554-019-00938-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,4]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["938"],"URL":"https:\/\/doi.org\/10.1007\/s11554-019-00938-y","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"type":"print","value":"1861-8200"},{"type":"electronic","value":"1861-8219"}],"subject":[],"published":{"date-parts":[[2020,1,4]]},"assertion":[{"value":"16 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}