Art

J-GLOBAL ID：202002235199689821   Reference number：20A2738885

aSNAQ: An adaptive stochastic Nesterov’s accelerated quasi-Newton method for training RNNs

aSNAQ:RNNを訓練するための適応型確率的Nesterovの加速準Newton法

Author (4)： Sendilkkumaar Indrapriyadarsini (Graduate School of Science and Technology, Shizuoka University) ,  Mahboubi Shahrzad (Graduate School of Electrical and Information Engineering, Shonan Institute of Technology) ,  Ninomiya Hiroshi (Graduate School of Electrical and Information Engineering, Shonan Institute of Technology) ,  Asai Hideki (Research Institute of Electronics, Shizuoka University)
Material： Nonlinear Theory and Its Applications, IEICE (Web)  (Nonlinear Theory Its Appl IEICE (Web))
Volume： 11  Issue： 4  Page： 409-421(J-STAGE)  Publication year： 2020 
JST Material Number： U0219A  ISSN： 2185-4106  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *neural network(biomodel) ,  regression model ,  quasi-Newton method ,  *machine learning ,  learning algorithm ,  computational complexity ,  gradient ,  curvature ,  computer programming ,  performance evaluation
Semi thesaurus term： *recurrent neural network ,  Learning performance ,  deep learning

Author keywords (5)： Recurrent neural network ,  training algorithm ,  Nesterov’s accelerated quasi-Newton ,  stochastic method ,  Tensorflow

JST classification (2)： Artificial intelligence  (JE08000Z) ,  Neurocomputers  (JC06010Q)

Reference (30)：

• [1] I. Sutskever, J. Martens, and G.E. Hinton, “Generating text with recurrent neural networks,” Proc. 28th ICML'11, pp. 1017-1024, June 2011.
• [2] O. Vinyals, A. Toshev, S. Bengio, and D. Erhan, “Show and tell: A neural image caption generator,” Proc. IEEE Conf. CVPR'15, pp. 3156-3164, 2015.
• [3] A. Karpathy and L. Fei-Fei, “Deep visual-semantic alignments for generating image descriptions,” Proc. IEEE Conf. CVPR'15, pp. 3128-3137, 2015.
• [4] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” arXiv preprint arXiv:1409.0473, September 2014
• [5] I. Sutskever, O. Vinyals, and Q.V. Le, “Sequence to sequence learning with neural networks,” Advances in Neural Information Processing Systems, pp. 3104-3112, 2014.

Terms in the title (5)： RNN ,  訓練 ,  確率 ,  加速 ,  準Newton法