{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:32:55Z","timestamp":1784140375419,"version":"3.55.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489156","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T18:25:09Z","timestamp":1539973509000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Fast Training and Model Compression of Gated RNNs via Singular Value Decomposition"],"prefix":"10.1109","author":[{"given":"Rui","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lefei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjian","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Neural networks with few multiplications","author":"lin","year":"2015","journal-title":"arXiv 1510 03009 in Proc ICLR 2016"},{"key":"ref11","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 in Proc ICLR 2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098035"},{"key":"ref15","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"3088","article-title":"Structured transforms for small-footprint deep learning","author":"sindhwani","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13560-1_65"},{"key":"ref18","article-title":"Factorization tricks for LSTM networks","author":"kuchaiev","year":"2017","journal-title":"arXiv 1703 10722 in Proc ICLR 2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1980.1102314"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref3","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Thirteenth Annual Con of the International Speech Communication Association"},{"key":"ref6","first-page":"622","article-title":"Artificial neural network computation on graphic process unit","volume":"1","author":"luo","year":"2005","journal-title":"Proceedings of IEEE International Joint Conference on Neural Networks (IJCNN’05)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1049\/el:19930841"},{"key":"ref7","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref9","article-title":"Computational cost reduction in learned transform classifications","author":"machado","year":"2015","journal-title":"arXiv 1504 06779"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF02288367"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref21","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref24","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref26","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","location":"Rio de Janeiro","start":{"date-parts":[[2018,7,8]]},"end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489156.pdf?arnumber=8489156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T20:38:52Z","timestamp":1598215132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489156","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}