Art

J-GLOBAL ID：202002230300965084   Reference number：20A0872097

A Robust Quasi-Newton Training with Adaptive Momentum for Microwave Circuit Models in Neural Networks

ニューラルネットワークにおけるマイクロ波回路モデルのための適応運動量によるロバストな準Newtonトレーニング

Author (4)： Mahboubi Shahrzad (Graduate School of Electrical and Information Engineering, Shonan Institute of Technology) ,  Sendillkkumaar Indrapriyadarsini (Graduate School of Integrated Science and Technology, Shizuoka University) ,  Ninomiya Hiroshi (Graduate School of Electrical and Information Engineering, Shonan Institute of Technology) ,  Asai Hideki (Research Institute of Electronics, Shizuoka University)
Material： Journal of Signal Processing (Web)  (信号処理(Web))
Volume： 24  Issue： 1  Page： 11-17(J-STAGE)  Publication year： 2020 
JST Material Number： U0425A  ISSN： 1880-1013  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *neural network(biomodel) ,  *microwave circuit ,  *circuit model ,  *momentum ,  *quasi-Newton method ,  nonlinearity ,  robustness ,  reference signal ,  algorithm
Semi thesaurus term： training sequence ,  signal processing algorithms

Author keywords (6)： neural networks ,  training algorithm ,  quasi-Newton method ,  Nesterov’s accelerated gradient ,  adaptive momentum term ,  microwave circuit modeling

JST classification (2)： Signal theory  (ND02020G) ,  Transmission circuit elements in general  (NC04010G)

Reference (20)：

• [1] S. Haykin: Neural Networks and Learning Machines, Pearson, 2009.
• [2] H. Kabir, L. Zhang, M. Yu, P. H. Aaen, J. Wood and Q. J. Zhang: Smart modeling of microwave devices, IEEE Microwave Mag., Vol.11, No.3, pp.105-118, 2010.
• [3] Q. J. Zhang, K. C. Gupta and V. K. Devabhaktuni: Artifical neural networks for RF and microwave design-from theory to practice, IEEE Trans. Microwave Theory and Tech., Vol.51, pp.1339-1350, 2003.
• [4] H. Ninomiya, S.Wan, H. Kabir, X. Zhang and Q. J. Zhang: Robust training of microwave neural network models using combined global/local optimization techniques, Proc. IEEE MTT-S International Microwave Symposium (IMS) Digest, pp.995-998, 2008.
• [5] I. Sutskever, J. Martens, G. Dahl and G. Hinton: On the importance of initialization and momentum in deep learning, Proc. IEEE International Conference on Machine Learning (ICML), 2013.

Terms in the title (7)： ニューラルネットワーク ,  マイクロ波回路 ,  モデル ,  適応 ,  運動量 ,  ロバスト ,  トレーニング