{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T20:41:10Z","timestamp":1725914470766},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319700953"},{"type":"electronic","value":"9783319700960"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-70096-0_32","type":"book-chapter","created":{"date-parts":[[2017,10,24]],"date-time":"2017-10-24T21:33:18Z","timestamp":1508880798000},"page":"305-314","source":"Crossref","is-referenced-by-count":1,"title":["Asynchronous, Data-Parallel Deep Convolutional Neural Network Training with Linear Prediction Model for Parameter Transition"],"prefix":"10.1007","author":[{"given":"Ikuro","family":"Sato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Fujisaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosuke","family":"Oyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akihiro","family":"Nomura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,26]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"32_CR1","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Van- houcke, V., Rabinovich, A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","key":"32_CR2","DOI":"10.1109\/CVPR.2015.7298594"},{"unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. In: International Conference on Learning Representations (2014)","key":"32_CR3"},{"issue":"3","key":"32_CR4","doi-asserted-by":"crossref","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(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"unstructured":"Krizhevsky, A., Ilya, S., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1097\u20131105 (2012)","key":"32_CR5"},{"unstructured":"Dean, J., Corrado, G.S., Monga, R., Chen, K., Devin, M., Le, Q.V., Mao, M.Z., Ranzato, M., Senior, A., Tucker, P., Yang, K., Ng, A.Y.: Large scale distributed deep Networks. In: Neural Information Processing Systems, pp. 1223\u20131231 (2012)","key":"32_CR6"},{"doi-asserted-by":"crossref","unstructured":"Iandola, F.N., Ashraf, K., Moskewicz, M.W., Keutzer, K.: Firecaffe: near-linear acceleration of deep neural network training on compute clusters arXiv:1511.00175 (2015)","key":"32_CR7","DOI":"10.1109\/CVPR.2016.284"},{"unstructured":"Zheng, S., Meng, Q., Wang, T., Chen, W., Yu, N., Ma, Z., Liu, T.: Asynchronous stochastic gradient descent with delay compensation for distributed deep learning arXiv:1609.08326 (2016)","key":"32_CR8"},{"unstructured":"Wu, R., Yan, S., Shan, Y., Dang, Q., Sun, G.: Deep Image: Scaling up image recognition arXiv:1501.02876 (2015)","key":"32_CR9"},{"doi-asserted-by":"crossref","unstructured":"Gupta, S., Zhang, W., Wang, F.: Model accuracy and runtime tradeoff in distributed deep learning: a systematic study. In: IEEE International Conference on Data Mining, pp. 171\u2013180 (2016)","key":"32_CR10","DOI":"10.1109\/ICDM.2016.0028"},{"unstructured":"Zhang, W., Gupta, S., Lian, X., Liu, J.: Staleness-aware async-SGD for distributed deep learning. In: International Joint Conferences on Artificial Intelligence, pp. 2350\u20132356 (2016)","key":"32_CR11"},{"unstructured":"MPI: A message-passing interface standard. http:\/\/mpi-forum.org\/docs\/mpi-3.1\/mpi31-report.pdf","key":"32_CR12"},{"doi-asserted-by":"crossref","unstructured":"Oyama, Y., Nomura, A., Sato, I., Nishimura, H., Tamatsu, Y., Matsuoka, S.: Predicting statistics of asynchronous SGD parameters for a large-scale distributed deep learning system on GPU supercomputers. In: IEEE Big Data, pp. 66\u201375 (2016)","key":"32_CR13","DOI":"10.1109\/BigData.2016.7840590"},{"unstructured":"Jaderberg, M., Czarnecki, W.M., Osindero, S., Vinyals, O., Graves, A., Kavukcuoglu, K.: Decoupled neural interfaces using synthetic gradients arXiv:1608.05343 (2016)","key":"32_CR14"},{"key":"32_CR15","first-page":"372","volume":"27","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method of solving a convex programming problem with convergence rate $$O (1\/k^2)$$ . Sov. Math. Dokl. 27, 372\u2013376 (1983)","journal-title":"Sov. Math. Dokl."},{"issue":"1","key":"32_CR16","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145\u2013151 (1999)","journal-title":"Neural Netw."},{"unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Master\u2019s thesis, Computer Science Department, University of Toronto (2009)","key":"32_CR17"},{"doi-asserted-by":"crossref","unstructured":"Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: IAPR International Conference on Document Analysis and Recognition, pp. 958\u2013963 (2003)","key":"32_CR18","DOI":"10.1109\/ICDAR.2003.1227801"},{"unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning, pp. 807\u2013814 (2010)","key":"32_CR19"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70096-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T23:30:00Z","timestamp":1570231800000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-70096-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319700953","9783319700960"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70096-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}