グローバルナビゲーションへ

本文へ

フッターへ

  1. ホーム
  2.  >  教員情報
  3.  >  大学院工学研究科 電気情報工学専攻
  4.  >  マハブービ シェヘラザード 助教

マハブービ シェヘラザード 助教

[研究指導課程]
博士前期課程

[取得学位]
博士（工学）
研究室ページ

専門・研究分野

人工知能、学習理論、最適化法

研究テーマ

  • ディープラーニングの高速化に関する研究

研究キーワード

人工ニューラルネットワーク、学習アルゴリズム、ディープラーニング

SDGsとの関連

主な研究業績

＜学術論文誌＞
  1. Shahrzad Mahboubi, Ryo Yamatomi, Indrapriyadarsini Sendilkkumaar, Hiroshi Ninomiya, and Hideki Asai:"On the Study of Memory-Less quasi-Newton Method with Momentum Term for Neural Network Training", IEICE NOLTA, vol.13-N, issue 2, pp.271-276, April 2022.
  2. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"Accelerating Symmetric Rank-1 Quasi-Newton Method with Nesterov’s Gradient for Training Neural Networks", Algorithms, MDPI, 2022, vol.15, issue 1, 6, https://doi.org/10.3390/a15010006, January 2022.
  3. Shahrzad Mahboubi, Indrapriyadarsini Sendilkkumaar, Hiroshi Ninomiya, and Hideki Asai:"Momentum Acceleration of quasi-Newton based Optimization Technique for Neural Network Training", IEICE NOLTA, vol.12-N, issue 3, pp.554-574, July 2021.
  4. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"A Nesterov’s Accelerated quasi-Newton method for Global Routing using Deep Reinforcement Learning", IEICE NOLTA, vol.12-N, issue 3, pp.323-335, July 2021.
  5. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"aSNAQ : An Adaptive Stochastic Nesterov’s Accelerated Quasi-Newton Method for Training RNNs", IEICE NOLTA, vol.11, issue 4, pp.409-421, October 2020.
  6. Shahrzad Mahboubi, Indrapriyadarsini Sendilkkumaar, Hiroshi Ninomiya, and Hideki Asai:"A Robust quasi-Newton Training with Adaptive Momentum for Microwave Circuit Models in Neural Networks", Journal of Signal Processing, vol. 24, no. 1, pp.11-17, January 2020.
  7. Shahrzad Mahboubi, and Hiroshi Ninomiya:"A Novel Training Algorithm based on Limited-Memory quasi-Newton Method with Nesterov’s Accelerated Gradient in Neural Networks and its Application to Highly-Nonlinear Modeling of Microwave Circuit", International Journal On Advances in Software, vol.11, no.3&4, pp.323-334, December 2018.

＜国際会議プロシーディング＞
  1. Shahrzad Mahboubi, and Hiroshi Ninomiya:"Weight Difference Propagation for Stochastic Gradient Descent Learning", Proc. IARIA The Eighteenth International Multi-Conference on Computing in the Global Information Technology, ICCGI 2023, pp.12-17, March 2023. (Virtual, Barcelona, Spain)
  2. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"A Stochastic Momentum Accelerated quasi-Newton Method for Neural Networks", Proc. 36th AAAI (Association for the Advancement of Artificial Intelligence) Conference on Artificial Intelligence, AAAI-2022, pp.12973-12974, February 2022. (Online)
  3. Shahrzad Mahboubi, Ryo Yamatomi, Indrapriyadarsini Sendilkkumaar, Hiroshi Ninomiya, and Hideki Asai:"On the Study of Memory-Less quasi-Newton Method with Momentum Term for Neural Network Training", Proc. 2021 IEICE Nonlinear Science Workshop (IEICE/NSW2021), December 2021. (Online)
  4. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"VLSI Physical Design Automation using Deep Reinforcement Learning", Poster presentation at WiML Workshop co-located with NeurIPS, December 2020.(Virtual)
  5. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"A Nesterov's Accelerated quasi-Newton method for Global Routing using Deep Reinforcement Learning", Proc. NOLTA 2020, pp.251–254, November 2020. (Virtual)
  6. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, Takeshi Kamio, and Hideki Asai:"A Neural Network Approach to Analog Circuit Design Optimization Using Nesterov's Accelerated Quasi-Newton Method", Proc. IEEE/ISCAS 2020, DOI: 10.1109/ISCAS45731.2020.9181152, October 2020. (Virtual, Seville, Spain)
  7. Sudeera M. D. H. Gunathilaka, Shahrzad Mahboubi, and Hiroshi Ninomiya:"Acceleration Technique of Two-Phase Quasi-Newton method with Momentum for Optimization Problem", Proc. IARIA The Twelfth International Conference on Information, Process, and Knowledge Management, eKNOW 2020, pp.17-19, March 2020. (Virtual, Valencia, Spain)
  8. Sota Yasuda,Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, and Hideki Asai:"A Stochastic Variance Reduced Nesterov’s Accelerated Quasi-Newton Method", Proc. IEEE/ICMLA 2019, pp.1874-1879, December 2019. (Boca Raton, Florida)
  9. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, and Hideki Asai:"An Adaptive Stochastic Nesterov Accelerated Quasi Newton Method for Training RNNs", Proc. NOLTA 2019, pp.208–211, December 2019. (Kuala Lumpur, Malaysia)
  10. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, and Hideki Asai:"A Stochastic Quasi-Newton Method with Nesterov’s Accelerated Gradient", Machine Learning and KnowLedge Discovery in Databases, Lecture Notes in Artificial Intelligence, Springer, and Proc. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD 2019, Part I, pp.743-760, September 2019. (Würzburg, Germany)
  11. Shahrzad Mahboubi, Indrapriyadarsini Sendilkkumaar, Hiroshi Ninomiya, and Hideki Asai:"Momentum acceleration of quasi-Newton Training for Neural Networks", Proc. The 16th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2019, pp.268–281, August 2019. (Yanuca Island, Cuvu, Fiji)
  12. Indrapriyadarsini Sendilkkumaar, Shahrzad Mahboubi, Hiroshi Ninomiya, and Hideki Asai:"Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow", Proc. IEEE/ICMLA 2018, pp.1147-1154, December 2018. (Orlando, Florida)
  13. Shahrzad Mahboubi, and Hiroshi Ninomiya:"A Novel Quasi-Newton with Momentum Training for Microwave Circuit Models Using Neural Networks", Proc. IEEE/ICECS 2018, pp.629-632, December 2018. (Bordeaux, FRANCE)
  14. Shahrzad Mahboubi, and Hiroshi Ninomiya:"A Novel Training Algorithm based on Limited-Memory quasi-Newton Method with Nesterov's Accelerated Gradient for Neural Networks", Proc. IARIA The Tenth International Conference on Future Computational Technologies and Applications, FUTURE COMPUTING 2018, pp.1-3, February 2018. (Barcelona, Spain)

主な所属学会

電子情報通信学会、IEEE

連絡先

E-mail：shaa [at] info.shonan-it.ac.jp （[at]を@に置き換えてください）

関連リンク

教員情報／情報学部
教員情報／工学部

教員情報

ホームへ戻る

ページの先頭へ戻る

資料請求
page top