著者

Yoshisuke Ueda

出版者

一般社団法人 電子情報通信学会

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.5, no.3, pp.252-258, 2014 (Released:2014-07-01)

参考文献数

8

被引用文献数

1 5

---

Attractors demonstrating randomly transitional (or chaotic) phenomena usually exhibit the following three outstanding properties: ·Sensitive dependence on initial conditions. ·Fractal structure of alpha-branches of principal saddles. ·Transitive property, i.e., one trajectory or sequence of images can come arbitrarily close to every point in the attractor. Among the three properties given above, the third property is always observed in simulation experiments. However, rigorous mathematical demonstration has not been provided yet. It supports the proposition that the omega branches of the principal saddle in a chaotic attractor must be basin-filling Peano curves.

著者

Makoto Mizuguchi Akitoshi Takayasu Takayuki Kubo Shin'ichi Oishi

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.7, no.3, pp.386-394, 2016 (Released:2016-07-01)

参考文献数

20

---

This paper is concerned with the embedding constant of the Sobolev type inequality for fractional derivatives on $\Omega\subset\mathbb{R}^{N}~(N\in\mathbb{N})$. The constant is explicitly described using the analytic semigroup over L2(Ω) generated by the Laplace operator. Some numerical examples of estimating the embedding constant are also provided.

著者

Yoshihiro Yonemura Yuichi Katori

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.12, no.2, pp.143-156, 2021 (Released:2021-04-01)

参考文献数

20

被引用文献数

3 6

---

We propose a hierarchical network model based on predictive coding and reservoir computing as a model of multi-modal sensory integration in the brain. The network is composed of visual, auditory, and integration areas. In each area, the dynamical reservoir acts as a generative model that reproduces the time-varying sensory signal. The states of the visual and auditory reservoir are spatially compressed and are sent to the integration area. We evaluate the model with a dataset of time courses, including a pair of visual (hand-written characters) and auditory (read utterances) signal. We show that the model learns the association of multiple modalities of the sensory signals and that the model reconstructs the visual signal from a given corresponding auditory signal. Our approach presents a novel dynamical mechanism of the multi-modal information processing in the brain and the fundamental technology for a brain like an artificial intelligence system.

著者

Yota Tsukamoto Honami Tsushima Tohru Ikeguchi

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.14, no.4, pp.677-690, 2023 (Released:2023-10-01)

参考文献数

29

---

The Izhikevich neuron model can reproduce various types of neurons, including chaotic neurons, by utilizing appropriate parameter sets. This study analyzes the responses of a periodically forced Izhikevich neuron with chaotic parameters using three measures—the diversity index, the coefficient of variation, and the local variation—to quantify interspike intervals (ISIs). The evaluation of ISIs combining these three measures clarifies the differences in neuronal activities, but evaluation using an individual measure cannot. In addition, we analyzed the change in the stability of the equilibrium points caused by a periodic input on a phase plane. The results indicate that in electrophysiologically feasible parameter sets, the stability of equilibrium points plays a crucial role in determining the critical amplitude around which irregular activities transition to regular ones. Thus, the relationship between neural behavior and the period and amplitude of the input current is contingent upon the existence and stability of equilibrium points.

著者

Masato Kawaguchi Hideyuki Kato

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.14, no.3, pp.590-608, 2023 (Released:2023-07-01)

参考文献数

32

---

Some studies started analyzing time series via complex networks in the noughties. A study reported that time series, which were transformed into networks via recurrence plots (RPs), especially k-nearest neighbor RP, exhibited superfamily phenomena resulting from the network motif analysis. However, it is not hard to imagine that the transformation properties drastically change the results of the motif analysis. In this study, we examine that by introducing another type of RP.As a result, the RP employed in this study works better for the superfamily phenomena among the time series than the previously used RP.

著者

Daisuke Oguchi Satoshi Moriya Hideaki Yamamoto Shigeo Sato

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.13, no.2, pp.427-433, 2022 (Released:2022-04-01)

参考文献数

10

被引用文献数

1

---

Reinforcement learning is promising as a machine learning paradigm in edge computing. However, its high computational cost poses a challenge when implementing in devices with limited circuit resources and power consumption. In this study, we investigated the relationship between the bit-length of floating-point operations and the learning performance of the reinforcement learning algorithm. In the case of the FrozenLake maze problem, we found that the learning performance of 8-bit floating-point arithmetic decreased, while that of 16-bit floating-point arithmetic was comparable to that of 64-bit CPU arithmetic. Our results provide a practical guideline for designing a dedicated reinforcement learning hardware with minimum circuit resources and power consumption.

著者

Tomoyuki Sasaki Hidehiro Nakano

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.14, no.2, pp.267-291, 2023 (Released:2023-04-01)

参考文献数

26

---

This paper relates to study on a new deterministic particle swarm optimization (D-PSO) called Optimizer based on Spiking Neural-oscillator Networks (OSNNs). OSNNs have a swarm consisting of plural particles which search a solution space interacting with each other. A single particle consists of plural spiking neural oscillators (`spiking oscillators') modeled by integrate-and-fire neurons. The spiking oscillators are coupled by a network topology and interact with each other by exchanging their own spike signals. Such interaction results in that coupling spiking oscillators can take synchronous or asynchronous dynamics and affects search performances of OSNNs. Herein we propose the basic algorithm of OSNNs and applied Ring 1-way network topology to coupling spiking oscillators. We theoretically analyzed parameter conditions for OSNNs, demonstrated the analytic results, and verified search performances of OSNNs through numerical simulations. We also herein discuss search performances of OSNNs and the relationship between the search performances and analytic results, and clarify prospective parameter regions which lead to good search performances in solving optimization problems.

著者

Rikuto Shigemi Hiroyasu Ando Kentaro Wada Risa Mukai

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.14, no.2, pp.416-427, 2023 (Released:2023-04-01)

参考文献数

12

---

Traffic congestion is closely associated with various social issues that must be solved urgently. With the recent advancement of machine learning technologies, diverse methods for predicting traffic congestion have been developed. Specifically, traffic prediction using deep learning can provide highly accurate performance. Nevertheless, several difficulties remain because of the complexity of deep learning models: particularly, they require large amounts of data and computational power. For this study, we strive to achieve traffic prediction precision using a simple linear model. Instead of improving complex models, we select training data appropriately with a linear model and then verify the feasibility of prediction by exploring “data complexity”. The prediction results imply that the linear model is as precise as deep learning even with fewer number of data and parameters. We use actual data from expressways collected using detectors.

著者

Sooyol Ok Suk-Hwan Lee

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.14, no.1, pp.2-17, 2023 (Released:2023-01-01)

参考文献数

29

被引用文献数

1

---

This paper proposes a technique for 360-degree panoramic video generating with multiple actual and virtual cameras in real-time. Our method acquires multiple images consisting of real images from physical cameras and virtual images from virtual cameras by GPU-based texture and encoding. Then, our method generates 360-degree panoramic images by ORB feature detection and matching to virtual and real images, automatic homography estimation based on the random absent consensus algorithm, multi-band blending and produces high-resolution video stream by Nvidia encoder based Hardware accelerated video encoding. From experimental results, we verified that our method takes at least 45fps at 2K resolution and 33fps at 4K resolution when transmitting the head mounted display stereo, enabling real-time 360-degree panoramic video generation as well as transmission.

著者

Takahiro Goto Yasuhiro Sugimoto Daisuke Nakanishi Keisuke Naniwa Koichi Osuka

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.13, no.4, pp.598-614, 2022 (Released:2022-10-01)

参考文献数

23

被引用文献数

1

---

This study focused on the bifurcation of coordination relationships between McKibben pneumatic actuators (MPA). We aimed to arrive at the control theory of a robot with MPAs by analyzing this bifurcation phenomena. The control law using the MPA tension generates multiple motion modes, and the coordination relationships between MPAs bifurcate depending on parameters reported in a previous study. The bifurcation phenomenon between two of those coordination relationships was analyzed and it was found that despite a similar link movement, the phase oscillators exhibited different coupled modes. The important difference between two coupled modes was determined to be the relationship between the MPA pressure and length. Further, we verified that the angular velocity of the link was the parameter that generated this phenomenon by analyzing it in correspondence with the model of forced oscillation. In addition, we confirmed the bifurcation phenomenon employing a 1-DOF pendulum machine.

著者

Indrapriyadarsini Sendilkkumaar Shahrzad Mahboubi Hiroshi Ninomiya Hideki Asai

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.11, no.4, pp.409-421, 2020 (Released:2020-10-01)

参考文献数

30

---

Recurrent Neural Networks (RNNs) are powerful sequence models that are particularly difficult to train. This paper proposes an adaptive stochastic Nesterov's accelerated quasi-Newton (aSNAQ) method for training RNNs. Several algorithms have been proposed earlier for training RNNs. However, due to high computational complexity, very few methods use second-order curvature information despite its ability to improve convergence. The proposed method is an accelerated second-order method that attempts to incorporate curvature information while maintaining a low per iteration cost. Furthermore, direction normalization has been introduced to solve the vanishing and/or exploding gradient problem that is prominent in training RNNs. The performance of the proposed method is evaluated in Tensorflow on benchmark sequence modeling problems. The results show that the proposed aSNAQ method is effective in training RNNs with a low per-iteration cost and improved performance compared to the second-order adaQN and first-order Adagrad and Adam methods.

著者

Siegfried M. Rump Masahide Kashiwagi

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.6, no.3, pp.341-359, 2015 (Released:2015-07-01)

参考文献数

31

被引用文献数

7 28

---

Affine arithmetic is a well-known tool to reduce the wrapping effect of ordinary interval arithmetic. We discuss several improvements both in theory and in terms of practical implementation. In particular details of INTLAB's affine arithmetic toolbox are presented. Computational examples demonstrate advantages and weaknesses of the approach.

著者

Kihei Magishi Tomoko Matsumoto Yutaka Shimada Tohru Ikeguchi

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.13, no.2, pp.343-348, 2022 (Released:2022-04-01)

参考文献数

22

---

Word co-occurrence networks (WCNs) are a major tool used to analyze languages quantitatively. In a WCN, the vertices are words (morphemes), and the edges connect n consecutive words in a sentence on the basis of the n-gram. Most studies use WCNs transformed at n=2. In this study, we investigated the changes in the structural features of WCNs when n increases using four types of documents for eight languages. We found that WCNs with n≧ 3 reflect features of the languages that do not appear when n = 2 and that some structural features evaluated by network measures depend on the text data.

著者

Taichi Fukawa Kenya Jin'no

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.13, no.2, pp.277-281, 2022 (Released:2022-04-01)

参考文献数

15

---

For an indefinite length spectrogram sequence of phonemes, we experimentally verified two methods of obtaining speaker embedding by transforming it to fixed length: adding padding and time stretching. We confirmed that both methods can maintain the extraction performance. We also confirm that the fixed frame length does not affect the results.

著者

Shin'ichi Oishi Kouta Sekine

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.12, no.3, pp.575-610, 2021 (Released:2021-07-01)

参考文献数

27

---

A computer assisted proof is presented for the existence of various periodic solutions for forced Suarez-Schopf's equation, which are delay differential equations modeling El Niño. Tight inclusions of periodic solutions are calculated through numerical verification method by utilizing a structure of Galerkin's equation for forced Suarez-Schopf's equation effectively. The existence of various periodic solutions has been proved via computer assisted proofs including various subharmonics. Especially, coexistence of several subharmonics are proved and numerical simulations are presented suggesting an appearance of chaos.

著者

Tomu Katsumata Muneki Yasuda

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.12, no.3, pp.377-390, 2021 (Released:2021-07-01)

参考文献数

29

被引用文献数

2

---

A deep Boltzmann machine (DBM) is a probabilistic deep learning model; DBM learning consists pretraining and fine-tuning stages. This study focuses on the fine-tuning stage, and it develops a new and effective fine-tuning method based on spatial Monte Carlo integration (SMCI), which is an extension of the standard Monte Carlo integration (MCI). It has been proved that SMCI is statistically more accurate than the standard MCI. Fine-tuning methods based on first-order and semi-second-order SMCI methods are formulated. The numerical experiments demonstrate that the proposed fine-tuning methods are superior to the conventional method in terms of both training and generalization errors.

著者

Daijiro Koyama Yunzhuo Wang Nobuyasu Shiga Satoshi Yasuda Nicolas Chauvet Makoto Naruse

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.12, no.2, pp.225-235, 2021 (Released:2021-04-01)

参考文献数

9

---

The growing demand of high-bandwidth and low-latency information transfer in information and communication technologies such as data centers and in-vehicle networks has increased the importance of optical communication networks in recent years. However, complicated arbitration schemes can impose significant overheads in data transfer, which may inhibit the full exploitation of the potential of optical interconnects. Herein, we propose an arbitration protocol based on precision time synchronization via wireless two-way interferometry (Wi-Wi), and numerically validate its efficiency including the ability to impose a strict upper bound on the latency of data transfer. We introduce the notion of arbitration point (AP) for a designated time duration, which is shared by all nodes thanks to the time synchronization by Wi-Wi, to determine data transmission while ensuring avoiding collision. Compared with the conventional carrier sense multiple access/collision detection (CSMA/CD)-based approach, a significant improvement in the data transfer was observed especially in the cases with high traffic flow rate. Furthermore, we conducted a proof-of-principle experiment for Wi-Wi-based data transfer between two electrically connected nodes and confirmed that the skew was less than 300 ns and remained stable over time. Conversely, non-Wi-Wi-based data transfer exhibited huge and unstable skew. These results indicate that precision time synchronization is a promising resource to reduce the communication overheads and ensure low latency for future networks and real-time applications.

著者

Aren Shinozaki Takaya Miyano Yoshihiko Horio

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.11, no.4, pp.466-479, 2020 (Released:2020-10-01)

参考文献数

20

被引用文献数

1

---

We have applied noisy echo state networks to the short-term forecasting of hyperchaotic and chaotic time series. The hyperchaotic time series were generated using the augmented Lorenz equations as a star network of Q nonidentical Lorenz systems and a four-dimensional Lorenz system. The echo state networks were used mainly in the recursive forecasting mode, wherein the output value of the network, i.e., the predicted value, at the current time step was recursively fed back to the input node at the next time step of prediction. The addition of external noise to the reservoir network has been found to considerably improve the fidelity of the geometrical structures of the chaotic attractors reconstructed from the predicted time series. We discuss these observations on the basis of Ueda's theory of chaos.

著者

Takashi Matsubara

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.11, no.1, pp.16-35, 2020 (Released:2020-01-01)

参考文献数

93

被引用文献数

2

---

Deep learning is considered to be a model-free, end-to-end, and black-box approach. It requires numerous data samples instead of expert knowledge on the target domain. Hence, it does not specify the mechanism and reasons for its decision making. This aspect is considered a critical limitation of deep learning. This paper introduces another viewpoint, namely Bayesian deep learning. Deep learning can be installed in any framework, such as Bayesian networks and reinforcement learning. Subsequently, an expert can implement the knowledge as the graph structure, accelerate learning, and obtain new knowledge on the target domain. The framework is termed as the deep generative model. Conversely, we can directly introduce the Bayesian modeling approach to deep learning. Subsequently, it is possible to explore deep learning with respect to the confidence of its decision making via uncertainty quantification of the output and detect wrong decision-making or anomalous inputs. Given the aforementioned approaches, it is possible to adjust the “brightness” of deep learning.

著者

Kaori Nagatou Takashi Morifuji

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

Nonlinear Theory and Its Applications, IEICE (ISSN:21854106)

巻号頁・発行日

vol.2, no.1, pp.111-122, 2011 (Released:2011-01-01)

参考文献数

13

被引用文献数

1

---

An enclosure method for complex eigenvalues of ordinary differential operatos is presented. We formulate the eigenvalue problem as a nonlinear system and apply a fixed point theorem to enclose eigenvalues and eigenfunctions or a basis of the corresponding invariant subspaces in case of multiple eigenvalues. Some enclosure examples are given.