Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NLP |
2022-11-25 11:10 |
Shiga |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
Chaotic time series and Ueda's theory of chaos Takaya Miyano (Ritsumeikan Univ.) NLP2022-72 |
In terms of Ueda’s theory of chaos, i.e., the concept of randomly transitional oscillations, we discuss the implications... [more] |
NLP2022-72 pp.71-72 |
NLP |
2022-08-02 09:25 |
Online |
Online |
Performance Evaluation of Time Series Forecasting with Chaotic Neural Network Reservoir using ReLU Derived Functions Tatsuya Saito, Misa Fujita (Chukyo Univ.) NLP2022-27 |
Reservoir computing has been attracting attention in recent years.
It can learn time-series data at high speed.
Th... [more] |
NLP2022-27 pp.7-10 |
NLP |
2021-12-18 14:50 |
Oita |
J:COM Horuto Hall OITA |
Experiment of time series signal classification task using 3D cyclic chaotic neural network reservoir Takemori Orima, Yoshihiko Horio (Tohoku Univ.) NLP2021-65 |
The chaotic neural network reservoir composed of chaotic neurons can perform time-series signal processing with a smalle... [more] |
NLP2021-65 pp.100-103 |
NLP |
2021-12-18 15:40 |
Oita |
J:COM Horuto Hall OITA |
Performance evaluation on timeseries prediction of multi-layer simple cycle reservoir computing Kentaro Imai, Masaharu Adachi (Tokyo Denki Univ.) NLP2021-67 |
The purpose of this study is to combine Deep Echo State Network with other models. In this study, we propose and impleme... [more] |
NLP2021-67 pp.110-113 |
RCC, MICT |
2019-05-29 15:30 |
Tokyo |
TOKYO BIG SIGHT |
[Poster Presentation]
Vibration time series analysis using persistent homology Koki Terauchi (Osaka City Univ.), Kazunori Hayashi (Osaka City Univ./RIKEN), Jing Di, Yoji Okada (SEI) RCC2019-10 MICT2019-10 |
In this research, in order to diagnose a failure of consumable parts of a rotating machine by using vibration time serie... [more] |
RCC2019-10 MICT2019-10 pp.47-52 |
NLP, NC (Joint) |
2019-01-23 11:00 |
Hokkaido |
The Centennial Hall, Hokkaido Univ. |
Performance Evaluation of Chaotic Random Numbers Using Integer Logistic Map by NIST Test Shiki Kanamaru (TUS), Yutaka Shimada (Saitama Univ.), Kantaro Fujiwara (UT), Tohru Ikeguchi (TUS) NLP2018-100 |
In this report, we generated pseudorandom numbers using chaotic dynamics and investigated its performance as pseudorando... [more] |
NLP2018-100 pp.23-28 |
NLP, CCS |
2018-06-08 09:45 |
Kyoto |
Kyoto Terrsa |
Application of tensor decomposition to chaotic itinerancy time series Takahiro Arai, Toshio Aoyagi (Kyoto Univ.) NLP2018-29 CCS2018-2 |
Tensor decomposition is a typical method for analyzing resting-state BOLD signals. This method can decompose the observe... [more] |
NLP2018-29 CCS2018-2 pp.7-12 |
NLP |
2017-11-05 17:25 |
Miyagi |
Research Institute of Electrical Communication Tohoku University |
Reconstructing Bifurcation Diagrams of Chaotic neuron Using Extreme Learning Machine Yoshitaka Itoh, Masaharu Adachi (Tokyo Denki Univ.) NLP2017-74 |
In recent year, an extreme learning machine which is simple structure have been applied to various problems. As one of t... [more] |
NLP2017-74 pp.53-58 |
NLP, CCS |
2015-06-12 14:00 |
Tokyo |
Waseda Univerisity |
Binary chaotic cryptography using augmented Lorenz equations Kenichiro Cho, Takaya Miyano (Rits Univ) NLP2015-62 CCS2015-24 |
Augmented Lorenz equations are expressed as a star network of N Lorenz subsystems sharing the scalar variable X as the c... [more] |
NLP2015-62 CCS2015-24 pp.135-137 |
SIS |
2013-06-14 10:50 |
Kagoshima |
Houzan Hall (Kagoshima) |
Modeling for Events characterizing Simultaneous Change in Time Series Parameters by using Coupled Pricing and Parameter Estimation based on Bayesian Method Shozo Tokinaga (Kyushu Univ.), Yoshikazu Ikeda (Kitakyushu Univ.) SIS2013-11 |
This report deals with
modeling for events characterizing simultaneous change in
time series parameters by using co... [more] |
SIS2013-11 pp.53-58 |
NLP |
2009-11-11 11:10 |
Kagoshima |
|
Chaotic Time Series Prediction by Combining Echo-State Networks and Radial Basis Function Networks Yoshitaka Itoh, Masaharu Adachi (Tokyo Denki Univ.) NLP2009-86 |
In this report, we describe a chaotic time series prediction method by a network which combines echo
state networks (ES... [more] |
NLP2009-86 pp.27-30 |
NC |
2009-01-20 10:00 |
Hokkaido |
Hokkaido Univ. |
[Invited Talk]
Chaotic itinerancy in the hippocampal CA3 and contractive affine transformations in CA1 provide a dynamical interpretation of complex memory Ichiro Tsuda (Hokkaido Univ.) NC2008-96 |
Since David Marr's pioneering paper entitled “Simple memory: A model for the archecortex” published in 1969, the functio... [more] |
NC2008-96 pp.85-86 |
NLP |
2008-12-10 16:30 |
Ishikawa |
|
Prediction of chaotic time series by neural networks with an improved particle swarm optimization Hironori Nakamura, Masaharu Adachi (Denki Univ.) NLP2008-91 |
In this report, we describe prediction of chaotic time series.
In concrete, we use neural networks as a prediction sys... [more] |
NLP2008-91 pp.113-118 |
NLP |
2008-03-27 15:00 |
Hyogo |
|
Analysis method of chaotic time series using measures of networks. Yutaka Shimada, Tohru Ikeguchi (Saitama Univ.) NLP2007-161 |
Complex phenomena are ubiquitous in the real world, for example, fluctuation of financial indices in a
stock market, po... [more] |
NLP2007-161 pp.43-48 |