{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:15:56Z","timestamp":1761581756626,"version":"build-2065373602"},"reference-count":24,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T00:00:00Z","timestamp":1539820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Convolutional neural networks have achieved remarkable improvements in image and video recognition but incur a heavy computational burden. To reduce the computational complexity of a convolutional neural network, this paper proposes an algorithm based on the Winograd minimal filtering algorithm and Strassen algorithm. Theoretical assessments of the proposed algorithm show that it can dramatically reduce computational complexity. Furthermore, the Visual Geometry Group (VGG) network is employed to evaluate the algorithm in practice. The results show that the proposed algorithm can provide the optimal performance by combining the savings of these two algorithms. It saves 75% of the runtime compared with the conventional algorithm.<\/jats:p>","DOI":"10.3390\/a11100159","type":"journal-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T10:55:41Z","timestamp":1539860141000},"page":"159","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks"],"prefix":"10.3390","volume":"11","author":[{"given":"Yulin","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"Key Laboratory of Information Technology for Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}]},{"given":"Donghui","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"Key Laboratory of Information Technology for Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"}]},{"given":"Leiou","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"Key Laboratory of Information Technology for Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"}]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"Key Laboratory of Information Technology for Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,10,18]]},"reference":[{"key":"ref_1","unstructured":"Simonyan, K., and Zisserman, A. (arXiv, 2014). Very deep convolutional networks for large-scale image recognition, arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"11215","DOI":"10.1109\/ACCESS.2018.2798799","article-title":"Exploiting Convolutional Neural Networks with Deeply Local Description for Remote Sensing Image Classification","volume":"6","author":"Liu","year":"2018","journal-title":"IEEE Access"},{"key":"ref_3","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). ImageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems."},{"key":"ref_4","unstructured":"Le, N.M., Granger, E., and Kiran, M. (December, January 28). A comparison of CNN-based face and head detectors for real-time video surveillance applications. Proceedings of the Seventh International Conference on Image Processing Theory, Tools and Applications, Montreal, QC, Canada."},{"key":"ref_5","unstructured":"Ren, S., He, K., and Girshick, R. (2014, January 8\u201313). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_6","unstructured":"Denil, M., Shakibi, B., and Dinh, L. (2013, January 5\u201310). Predicting Parameters in Deep Learning. Proceedings of the International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_7","unstructured":"Han, S., Pool, J., and Tran, J. (2015, January 9\u201312). Learning both Weights and Connections for Efficient Neural Networks. Proceedings of the International Conference on Neural Information Processing Systems, Istanbul, Turkey."},{"key":"ref_8","unstructured":"Guo, Y., Yao, A., and Chen, Y. (2016). Dynamic Network Surgery for Efficient DNNs. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Qiu, J., Wang, J., and Yao, S. (2016, January 21\u201323). Going Deeper with Embedded FPGA Platform for Convolutional Neural Network. Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, CA, USA.","DOI":"10.1145\/2847263.2847265"},{"key":"ref_10","unstructured":"Courbariaux, M., Bengio, Y., and David, J.P. (arXiv, 2014). Low Precision Arithmetic for Deep Learning, arXiv."},{"key":"ref_11","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., and Narayanan, P. (2015, January 7\u20139). Deep Learning with Limited Numerical Precision. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., and Redmon, J. (2016, January 11\u201314). XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref_13","unstructured":"Zhu, C., Han, S., and Mao, H. (2017, January 24\u201326). Trained Ternary Quantization. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zou, J., Ming, X., and Sun, J. (2014, January 7\u201312). Efficient and accurate approximations of nonlinear convolutional networks. Proceedings of the Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"ref_15","unstructured":"Mathieu, M., Henaff, M., Lecun, Y., Chintala, S., Piantino, S., and Lecun, Y. (arXiv, 2013). Fast Training of Convolutional Networks through FFTs, arXiv."},{"key":"ref_16","unstructured":"Vasilache, N., Johnson, J., and Mathieu, M. (2015, January 7\u20139). Fast Convolutional Nets with fbfft: A GPU Performance Evaluation. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_17","first-page":"496","article-title":"The complexity of a scheme of functional elements simulating the multiplication of integers","volume":"150","author":"Toom","year":"1963","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"ref_18","unstructured":"Cook, S.A. (1966). On the Minimum Computation Time for Multiplication. [Ph.D. Thesis, Harvard University]."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Winograd, S. (1980). Arithmetic Complexity of Computations, SIAM.","DOI":"10.1137\/1.9781611970364"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1750039","DOI":"10.1142\/S0129065717500393","article-title":"A novel multilayer correlation maximization model for improving CCA-based frequency recognition in SSVEP brain-computer interface","volume":"28","author":"Jiao","year":"2018","journal-title":"Int. J. Neural Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"81","DOI":"10.3233\/ICA-150502","article-title":"An adaptive neural network approach for operator functional state prediction using psychophysiological data","volume":"23","author":"Wang","year":"2015","journal-title":"Integr. Comput. Aided Eng."},{"key":"ref_22","unstructured":"Lavin, A., and Gray, S. (July, January 26). Fast Algorithms for Convolutional Neural Networks. Proceedings of the Computer Vision and Pattern Recognition, Caesars Palace, NV, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1007\/BF02165411","article-title":"Gaussian elimination is not optimal","volume":"13","author":"Strassen","year":"1969","journal-title":"Numer. Math."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cong, J., and Xiao, B. (2014, January 15\u201319). Minimizing Computation in Convolutional Neural Networks. Proceedings of the Artificial Neural Networks and Machine Learning\u2014ICANN 2014, Hamburg, Germany.","DOI":"10.1007\/978-3-319-11179-7_36"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/11\/10\/159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:26:29Z","timestamp":1760196389000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/11\/10\/159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,18]]},"references-count":24,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2018,10]]}},"alternative-id":["a11100159"],"URL":"https:\/\/doi.org\/10.3390\/a11100159","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2018,10,18]]}}}