Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
ITE-ME, EMM, IE, LOIS, IEE-CMN, IPSJ-AVM [detail] |
2021-08-26 16:20 |
Online |
Online |
[Invited Talk]
On the Simulations of Spreading COVID-19 by the Artificial Intelligence Research Center, College of Industrial Technology, Nihon University Yuto Omae, Jun Toyotani, Kazuyuki Hara, Yasuhiro Gon (NU), Hirotaka Takahashi (TCU) LOIS2021-22 IE2021-17 EMM2021-52 |
[more] |
LOIS2021-22 IE2021-17 EMM2021-52 pp.33-37 |
ICTSSL |
2021-07-08 15:00 |
Online |
Online |
Management model of taking seats for restaurant considering COVID-19 infection risk Yohei Kakimoto, Yuto Omae, Jun Toyotani, Kazuyuki Hara (Nihon Univ.), Hirotaka Takahashi (Tokyo City Univ.) ICTSSL2021-11 |
By an epidemic of COVID-19, many restaurants have been operated following the guidelines for infection prevention. To re... [more] |
ICTSSL2021-11 pp.17-21 |
ICTSSL |
2021-07-08 15:25 |
Online |
Online |
A mathematical model for verifying the effect of COVID-19 Contact-Confirming Application (COCOA) on reducing infectors
-- On the case of GoTo travel campaign -- Ryota Maehashi, Rian Nagaoka, Yuka Nigoshi, Yuga Hayashi, Ryuhei Moriguchi (THS), Yohei Kakimoto, Jun Toyotani, Kazuyuki Hara (NU), Hirotaka Takahashi (TCU), Yuto Omae (NU) ICTSSL2021-12 |
(To be available after the conference date) [more] |
ICTSSL2021-12 pp.22-26 |
AI |
2021-02-12 09:05 |
Online |
Online |
Effectiveness of Strategy of Cancelling Stay-at-home Orders on the Number of COVID-19 Infectors and Outgoing People
-- Strategies Verification based on Multi-agent simulation -- Yuto Omae (NU), Yohei Kakimoto (HU), Jun Toyotani, Kazuyuki Hara, Yasuhiro Gon (NU), Hirotaka Takahashi (TCU) AI2020-22 |
(To be available after the conference date) [more] |
AI2020-22 pp.1-6 |
IA, IN (Joint) |
2020-12-15 10:25 |
Online |
Online |
Agent-based Infection Spreading Simulation for Verifying Effectiveness of the COVID-19 Contact-Confirming Application Incorporating Secondary Indirect Contact Notification Function Yuto Omae, Jun Toyotani, Kazuyuki Hara, Yasuhiro Gon (NU), Hirotaka Takahashi (TCU) IN2020-39 |
[more] |
IN2020-39 pp.37-42 |
LOIS, EMM, IE, IEE-CMN, ITE-ME, IPSJ-AVM [detail] |
2020-09-02 09:30 |
Online |
Online |
Verification of the Effect of the COVID-19 Contact-Confirming Application on Decreasing the Number of Infected Persons Based on a Multi Agent Simulation Yuto Omae, Jun Toyotani, Kazuyuki Hara, Yasuhiro Gon (NU), Hirotaka Takahashi (TCU) LOIS2020-9 IE2020-21 EMM2020-33 |
(To be available after the conference date) [more] |
LOIS2020-9 IE2020-21 EMM2020-33 pp.25-30 |
IBISML |
2017-11-10 13:00 |
Tokyo |
Univ. of Tokyo |
Analysis of Dropout in online learning Kazuyuki Hara (Nihon Univ.) IBISML2017-61 |
Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition.
This learning... [more] |
IBISML2017-61 pp.201-206 |
NC, NLP (Joint) |
2016-01-29 15:50 |
Fukuoka |
Kyushu Institute of Technology |
Node-perturbation Learning for Soft-committee machine Kazuyuki Hara (Nihon Univ.), Kentaro Katahira (Nagoya Univ.) NC2015-66 |
Node perturbation learning is a stochastic gradient descent method for neural networks. It estimates the gradient of the... [more] |
NC2015-66 pp.49-54 |
NC, NLP (Joint) |
2016-01-29 16:15 |
Fukuoka |
Kyushu Institute of Technology |
Proposal of novel dropout method and its analysis of dynamic property Daisuke Saitoh, Tasuku Kondo, Kazuyuki Hara (Nihon Univ.) NC2015-67 |
Deep learning that use a large network and includes many units tends to occur the overfitting. Therefore, to avoid the o... [more] |
NC2015-67 pp.55-60 |
NC, MBE (Joint) |
2013-07-19 14:30 |
Tokushima |
The University of Tokushima |
Statistical Mechanics of node-perturbation Learning using two independent noises Kazuyuki Hara (Nihon Univ.), Kentaro Katahira, Masato Okada (Univ. of Tokyo) NC2013-17 |
Node perturbation learning is a stochastic gradient descent method for neural networks. It estimates the gradient by com... [more] |
NC2013-17 pp.13-18 |
NC |
2011-10-20 13:10 |
Fukuoka |
Ohashi Campus, Kyushu Univ. |
Statistical Mechanics of Node-Perturbation Learning for Nonlinear Perceptron Kazuyuki Hara (Nihon Univ.), Kentaro Katahira (JST), Kazuo Okanoya (RIKEN), Masato Okada (Tokyo Univ.) NC2011-63 |
Node-perturbation learning is a kind of statistical gradient descent algorithm that can be applied to problems where the... [more] |
NC2011-63 pp.107-112 |
NC, NLP |
2009-07-14 13:00 |
Nara |
NAIST |
Statistical Mechanics of Node-perturbation learning Kazuyuki Hara (Tokyo Metro. Colle. Ind. Eng.), Kentaro Katahira (ERATO), Kazuo Okanoya (RIKEN), Masato Okada (Tokyo Univ.) NLP2009-38 NC2009-31 |
Node-perturbation learning is a stochastic gradient method, and it can
apply to the problem where the objective functi... [more] |
NLP2009-38 NC2009-31 pp.127-132 |
NC, MBE (Joint) |
2009-03-13 13:25 |
Tokyo |
Tamagawa Univ. |
Infant's Indoor Behavior Recognition using Bayesian Inference in combination with Tree Augumented Naive Bayes and Baysian Network Shouzou Ishikawa (Tokyo Metropolitan Coll. of Ind Tech.), Yoichi Motomura, Yoshifumi Nishida (Digital Human Resarch Center,National Inst. of Adv Ind and Tech.), Kazuyuki Hara (Tokyo Metropolitan Coll. of Ind Tech.) NC2008-156 |
The purpose of this study is to prevent injury in children.
It is important to recognize and observe infant's behavior ... [more] |
NC2008-156 pp.313-318 |
NC |
2008-11-08 15:30 |
Saga |
Saga Univ. |
Statistical Mechanics of Partial Annealing
-- Mexican-hat-type interaction case -- Kazuyuki Hara (Tokyo Metro. College), Tatsuya Uezu (Nara Women's Univ.), Seiji Miyoshi (Kansai Univ.), Masato Okada (Tokyo Univ.) NC2008-72 |
We analyzed the equilibrium states of an Ising spin neural network model
in which both spins and interactions evolve s... [more] |
NC2008-72 pp.79-83 |
NC |
2006-03-16 13:50 |
Tokyo |
Tamagawa University |
Mutual Learning Involves Integration Mechanizm of Ensemble Learning Kazuyuki Hara (Tokyo Metor. College), Masato Okada (Univ. Tokyo) |
In the previous report, we derived differential equations of the order
parameter of mutual learning using students prev... [more] |
NC2005-144 pp.115-120 |