Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NLP |
2023-05-13 10:50 |
Fukushima |
Kenshin Koriyama Cultural Center (Koriyama, Fukushima) |
Study on the Effectiveness of Adaptive Gradient Algorithm with Momentum on Spatiotemporal Second-Order Dynamics Model Shahrzad Mahboubi, Hiroshi Ninomiya (SIT) NLP2023-3 |
[more] |
NLP2023-3 pp.11-15 |
CCS |
2023-03-26 13:55 |
Hokkaido |
RUSUTSU RESORT |
Study on tge Implementation of AI for Generating Humorous Response Sentence to Image Using AutoEncoder and Pix2Seq Ryo Yamatomi, Shahrzad Mahboubi, Hiroshi Ninomiya (SIT) CCS2022-73 |
[more] |
CCS2022-73 pp.59-62 |
CCS, NLP |
2022-06-09 16:50 |
Osaka |
(Primary: On-site, Secondary: Online) |
A Study on Accelerating Stochastic Weight Difference Propagation with Momentum Term Shahrzad Mahboubi, Hiroshi Ninomiya (Shonan Inst. of Tech.) NLP2022-9 CCS2022-9 |
With the rapid development of the IoT, there has been an increasing need to process the data on microcomputers equipped ... [more] |
NLP2022-9 CCS2022-9 pp.40-45 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-21 15:35 |
Online |
Online |
On the Study of Stochastic Gradient Descent Learning using Weight Difference Propagation Shahrzad Mahboubi, Ryo Yamatomi, Hiroshi Ninomiya (Shonan Inst. of Tech.) NLP2021-88 MICT2021-63 MBE2021-49 |
[more] |
NLP2021-88 MICT2021-63 MBE2021-49 pp.61-66 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-21 16:00 |
Online |
Online |
On the Study of Second-Order Training Algorithm using Matrix Diagonalization based on Hutchinson estimation Ryo Yamatomi, Shahrzad Mahboubi, Hiroshi Ninomiya (Shonan Inst. Tec.) NLP2021-89 MICT2021-64 MBE2021-50 |
In this study, we propose a new training algorithm based on the second-order approximated gradient method, which aims to... [more] |
NLP2021-89 MICT2021-64 MBE2021-50 pp.67-70 |
NLP, NC (Joint) |
2020-01-24 13:10 |
Okinawa |
Miyakojima Marine Terminal |
Optimization of CMOS operational amplifier using MOGA Hitoshi Kubo (Shizuoka Univ.), Hiroshi Ninomiya (Shonan Inst. of Tech.), Hideki Asai (Shizuoka Univ.) NLP2019-93 |
Multi-Objective Genetic Algorithm (MOGA) is an extended version of Genetic Algorithm (GA) for problems with multiple obj... [more] |
NLP2019-93 pp.45-48 |
NLP, MSS (Joint) |
2019-03-15 14:55 |
Fukui |
Bunkyo Camp., Univ. of Fukui |
On the Influence of Momentum term in quasi-Newton method Shahrzad Mahboubi (SIT), Indrapriyadarsini s (Shizuoka Univ.), Hiroshi Ninomiya (SIT), Hideki Asai (Shizuoka Univ.) NLP2018-137 |
The Nesterov's Accelerated quasi-Newton (NAQ) method was derived from the quadratic approximation of the error function ... [more] |
NLP2018-137 pp.69-74 |
NLP |
2017-07-13 13:25 |
Okinawa |
Miyako Island Marine Terminal |
On the Efficiency of Limited-Memory quasi-Newton Training using Second-Order Approximation Gradient Model with Inertial Term Shahrzad Mahboubi, Hiroshi Ninomiya (SIT) NLP2017-32 |
In recent years, along with large-scale data, it is expected that the scale of neural network will be large too. Therefo... [more] |
NLP2017-32 pp.23-28 |
NC, NLP (Joint) |
2016-01-29 12:10 |
Fukuoka |
Kyushu Institute of Technology |
Accelerated quasi-Newton Training using Nesterov's Gradient Method Hiroshi Ninomiya (SIT) NLP2015-141 |
This paper describes a new quasi-Newton based accelerated technique for training of neural networks. Recently, Nesterov’... [more] |
NLP2015-141 pp.87-92 |
VLD, CPSY, RECONF, IPSJ-SLDM, IPSJ-ARC [detail] |
2016-01-19 10:40 |
Kanagawa |
Hiyoshi Campus, Keio University |
Circuit Design of Reconfigurable Logic and Comparison of the Methods Junki Kato, Shigeyoshi Watanabe, Hiroshi Ninomiya, Manabu Kobayashi, Yasuyuki Miura (SIT) VLD2015-77 CPSY2015-109 RECONF2015-59 |
[more] |
VLD2015-77 CPSY2015-109 RECONF2015-59 pp.1-6 |
SDM, ICD |
2015-08-25 10:20 |
Kumamoto |
Kumamoto City |
Circuit Design of Reconfigurable Dynamic Logic and Estimation of Number of Elements Junki Kato, Shigeyoshi Watanabe, Hiroshi Ninomiya, Manabu Kobayashi, Yasuyuki Miura (SIT) SDM2015-66 ICD2015-35 |
[more] |
SDM2015-66 ICD2015-35 pp.47-52 |
ET |
2015-03-14 15:40 |
Tokushima |
Shikoku Univ. Plaza |
Establishment of an Active Engineering Learning Center on the basis of a Visualization Hideaki Okazaki, Fumihiro Inoue (Shonan Inst. Tech.), Michiya Inoue (Tokyo D Univ), Fumio Ozaki, Toshiaki Kagawa, Hiroyuki Sato, Hiroshi Takahashi, Toshihiro Tachibana, Kaya Nagasawa, Hiroshi Ninomiya, Takako Nonaka, Hikaru Mizutani (Shonan Inst. Tech.) ET2014-93 |
We show an establishment of an active engineering learning center on the basis of a visualization, and especially presen... [more] |
ET2014-93 pp.45-49 |
RECONF, CPSY, VLD, IPSJ-SLDM [detail] |
2015-01-29 10:45 |
Kanagawa |
Hiyoshi Campus, Keio University |
Circuit Design and Valuation of Reconfigurable Logic Circuit. Junki Kato, Shigeyoshi Watanabe, Hiroshi Ninomiya, Manabu Kobayashi, Yasuyuki Miura (SIT) VLD2014-119 CPSY2014-128 RECONF2014-52 |
[more] |
VLD2014-119 CPSY2014-128 RECONF2014-52 pp.35-40 |
VLD, DC, IPSJ-SLDM, CPSY, RECONF, ICD, CPM (Joint) [detail] |
2014-11-27 16:50 |
Oita |
B-ConPlaza |
Circuit Design of Reconfigurable Dynamic Logic Junki Kato, Shigeyoshi Watanabe, Hiroshi Ninomiya, Manabu Kobayashi, Yasuyuki Miura (Shonan Inst. of Tech.) CPM2014-126 ICD2014-69 |
[more] |
CPM2014-126 ICD2014-69 pp.21-26 |
ICD, SDM |
2014-08-05 14:20 |
Hokkaido |
Hokkaido Univ., Multimedia Education Bldg. |
Circuit Design of Reconfigurable Dynamic Logic Based on Double Gate MOSFETs Junki Kato, Shigeyoshi Watanabe, Hiroshi Ninomiya, Manabu Kobayashi, Yasuyuki Miura (SIT) SDM2014-78 ICD2014-47 |
[more] |
SDM2014-78 ICD2014-47 pp.87-92 |
NLP |
2013-07-09 10:00 |
Okinawa |
Miyako Island Marine Terminal |
Dynamic Sample Size Selection based quasi-Newton Training for Multilayer Neural Networks Hiroshi Ninomiya (SIT) NLP2013-38 |
This paper describes a novel robust training algorithm based on quasi-Newton iteration with the dynamic sample size sele... [more] |
NLP2013-38 pp.63-68 |
NC, NLP |
2013-01-24 12:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Study of qusai-Newton training algorithm on parallel distributed environment Makoto Saiki, Yoshihiko Sakashita, Hiroshi Ninomiya (Shonan Inst. of Tech.) NLP2012-111 NC2012-101 |
This paper describes the feasibility of quasi-Newton method for training feedforward neural networks on the parallel dis... [more] |
NLP2012-111 NC2012-101 pp.43-48 |
IT |
2012-09-28 11:30 |
Gunma |
Kusatsu Seminar House |
A Quantizer Design Method Based on Mutual Information Criteria for MIMO System Manabu Kobayashi (SIT), Hideki Yagi (UEC), Hiroshi Ninomiya (SIT), Shigeichi Hirasawa (Waseda Univ.) IT2012-41 |
B. M. Kurkoski et al. have proposed a quantizer design method based on the maximization of the mutual information.
Furt... [more] |
IT2012-41 pp.59-64 |
NLP |
2011-11-09 16:20 |
Okinawa |
Miyako Island Marine Terminal |
Robust Training of the Feedforward Neural Networks using hybrid quasi-Newton Training Algorithm Toshikazu Abe, Yoshihiko Sakashita, Hiroshi Ninomiya (SIT) NLP2011-105 |
Various techniques based on the gradient descent method have been studied as training algorithms for neuralnetworks. Neu... [more] |
NLP2011-105 pp.75-80 |
NLP |
2011-03-11 14:45 |
Tokyo |
Tokyo University of Science |
A Study on Effect of Feeding Method of Training Data in Improved online quasi-Newton Training Algorithm Toshikazu Abe, Yoshihiko Sakashita, Hiroshi Ninomiya (Shonan Inst. of Tech.) NLP2010-192 |
[more] |
NLP2010-192 pp.163-168 |