arXiv subjects

Nozomi Akashi

Publications and source records attributed to Nozomi Akashi.

11 recordsLinked to original sources

arXiv2026

Recycling computational processes of dynamic programming for combinatorial optimization problems: a reservoir computing approach

Reusing previously computed results is a long-standing principle for reducing computational cost, but such reuse has largely been confined to a single problem's computation. Sharing computational processes across multiple simultaneously solved problems remains possible in principle, yet designing algorithms that exploit nontrivial cross-task relationships is difficult to do manually. Here, we use machine learning to discover such algorithms automatically. Specifically, based on reservoir computing, we propose a method that uses computation results recorded by dynamic programming for combinatorial optimization problems as features for linear regression, leveraging them to assist other combinatorial optimization computations. We validate the approach on the traveling salesman and subset sum problems. Multiplexing the dynamic programming process improves approximation accuracy over generic features and reduces computation time compared with independent solutions. These results suggest a new form of computation, distinct from conventional computational design, in which multiple processes efficiently share and recycle intermediate results and states.

cs.LG↗

arXiv2026

One-shot prediction of noise-induced bifurcations with reservoir computing

Dynamical systems can exhibit complex responses when noise is injected. In particular, dynamics can be qualitatively altered by dynamic noise, a phenomenon known as noise-induced bifurcation. Predicting noise-induced bifurcations is a critical challenge in nonlinear physics. Recently, it has been reported that reservoir computing, a machine learning framework, can reconstruct the unseen global structure of a dynamical system, including bifurcations, from limited time series data. However, learning global structures in random dynamical systems has not yet been systematically addressed. In this study, we report that a simple reservoir computing framework can predict the noise-induced bifurcation structure from the time series at a single noise condition. We demonstrate dynamic noise cancellation and the reconstruction of entire noise-induced bifurcation structures, including noise-induced chaos and noise-induced order, in representative dynamical systems. Additionally, we provide a theoretical explanation for noise cancellation and demonstrate noise cancellation of a neuromorphic spintronics device. Our results provide significant insights into understanding and harnessing real-world noisy complex dynamics.

nlin.CD↗

arXiv2025

Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics

Machine learning methods have shown promise in learning chaotic dynamical systems, enabling model-free short-term prediction and attractor reconstruction. However, when applied to large-scale, spatiotemporally chaotic systems, purely data-driven machine learning methods often suffer from inefficiencies, as they require a large learning model size and a massive amount of training data to achieve acceptable performance. To address this challenge, we incorporate the spatial coupling structure of the target system as an inductive bias in the network design. Specifically, we introduce physics-guided clustered echo state networks, leveraging the efficiency of the echo state networks as a base model. Experimental results on benchmark chaotic systems demonstrate that our physics-informed method outperforms existing echo state network models in learning the target chaotic systems. Additionally, we numerically demonstrate that leveraging coupling knowledge into ESN models can enhance their robustness to variations of training and target system conditions. We further show that our proposed model remains effective even when the coupling knowledge is imperfect or extracted directly from time series data. We believe this approach has the potential to enhance other machine-learning methods.

nlin.CD↗

arXiv2024

Gradient-based optimization of spintronic devices

The optimization of physical parameters serves various purposes, such as system identification and efficiency in developing devices. Spin-torque oscillators have been applied to neuromorphic computing experimentally and theoretically, but the optimization of their physical parameters has usually been done by grid search. In this paper, we propose a scheme to optimize the parameters of the dynamics of macrospin-type spin-torque oscillators using the gradient descent method with automatic differentiation. First, we prepared numerically created dynamics as teacher data and successfully tuned the parameters to reproduce the dynamics. This can be applied to obtain the correspondence between the simulation and experiment of the spin-torque oscillators. Next, we successfully solved the image recognition task with high accuracy by connecting the coupled system of spin-torque oscillators to the input and output layers and training all of them through gradient descent. This approach allowed us to estimate how to control the experimental setup and design the physical systems so that the task could be solved with a high accuracy using spin-torque oscillators.

cond-mat.mes-hall↗

arXiv2024

Exploiting Chaotic Dynamics as Deep Neural Networks

Chaos presents complex dynamics arising from nonlinearity and a sensitivity to initial states. These characteristics suggest a depth of expressivity that underscores their potential for advanced computational applications. However, strategies to effectively exploit chaotic dynamics for information processing have largely remained elusive. In this study, we reveal that the essence of chaos can be found in various state-of-the-art deep neural networks. Drawing inspiration from this revelation, we propose a novel method that directly leverages chaotic dynamics for deep learning architectures. Our approach is systematically evaluated across distinct chaotic systems. In all instances, our framework presents superior results to conventional deep neural networks in terms of accuracy, convergence speed, and efficiency. Furthermore, we found an active role of transient chaos formation in our scheme. Collectively, this study offers a new path for the integration of chaos, which has long been overlooked in information processing, and provides insights into the prospective fusion of chaotic dynamics within the domains of machine learning and neuromorphic computation.

cs.NE↗

arXiv2023

Virtual reservoir acceleration for CPU and GPU: Case study for coupled spin-torque oscillator reservoir

We provide high-speed implementations for simulating reservoirs described by $N$-coupled spin-torque oscillators. Here $N$ also corresponds to the number of reservoir nodes. We benchmark a variety of implementations based on CPU and GPU. Our new methods are at least 2.6 times quicker than the baseline for $N$ in range $1$ to $10^4$. More specifically, over all implementations the best factor is 78.9 for $N=1$ which decreases to 2.6 for $N=10^3$ and finally increases to 23.8 for $N=10^4$. GPU outperforms CPU significantly at $N=2500$. Our results show that GPU implementations should be tested for reservoir simulations. The implementations considered here can be used for any reservoir with evolution that can be approximated using an explicit method.

cs.DC↗

arXiv2023

Embedding bifurcations into pneumatic artificial muscle

Harnessing complex body dynamics has been a long-standing challenge in robotics. Soft body dynamics is a typical example of high complexity in interacting with the environment. An increasing number of studies have reported that these dynamics can be used as a computational resource. This includes the McKibben pneumatic artificial muscle, which is a typical soft actuator. This study demonstrated that various dynamics, including periodic and chaotic dynamics, could be embedded into the pneumatic artificial muscle, with the entire bifurcation structure using the framework of physical reservoir computing. These results suggest that dynamics that are not presented in training data could be embedded by using this capability of bifurcation embeddment. This implies that it is possible to embed various qualitatively different patterns into pneumatic artificial muscle by learning specific patterns, without the need to design and learn all patterns required for the purpose. Thus, this study sheds new light on a novel pathway to simplify the robotic devices and training of the control by reducing the external pattern generators and the amount and types of training data for the control.

cs.RO↗

arXiv2020

Step-like dependence of memory function on pulse width in spintronics reservoir computing

Physical reservoir computing is a type of recurrent neural network that applies the dynamical response from physical systems to information processing. However, the relation between computation performance and physical parameters/phenomena still remains unclear. This study reports our progress regarding the role of current-dependent magnetic damping in the computational performance of reservoir computing. The current-dependent relaxation dynamics of a magnetic vortex core results in an asymmetric memory function with respect to binary inputs. A fast relaxation caused by a large input leads to a fast fading of the input memory, whereas a slow relaxation by a small input enables the reservoir to keep the input memory for a relatively long time. As a result, a step-like dependence is found for the short-term memory and parity-check capacities on the pulse width of input data, where the capacities remain at 1.5 for a certain range of the pulse width, and drop to 1.0 for a long pulse-width limit. Both analytical and numerical analyses clarify that the step-like behavior can be attributed to the current-dependent relaxation time of the vortex core to a limit-cycle state. }

cond-mat.mes-hall↗

arXiv2020

Periodic structure of memory function in spintronics reservoir with feedback current

The role of the feedback effect on physical reservoir computing is studied theoretically by solving the vortex-core dynamics in a nanostructured ferromagnet. Although the spin-transfer torque due to the feedback current makes the vortex dynamics complex, it is clarified that the feedback effect does not always contribute to the enhancement of the memory function in a physical reservoir. The memory function, characterized by the correlation coefficient between the input data and the dynamical response of the vortex core, becomes large when the delay time of the feedback current is not an integral multiple of the pulse width. On the other hand, the memory function remains small when the delay time is an integral multiple of the pulse width. As a result, a periodic behavior for the short-term memory capacity is observed with respect to the delay time, the phenomenon of which can be attributed to correlations between the virtual neurons via the feedback current.

cond-mat.mes-hall↗

arXiv2019

Synchronization and chaos in a spin-torque oscillator with a perpendicularly magnetized free layer

Synchronization and chaos caused by alternating current and microwave field in a spin torque oscillator consisting of a perpendicularly magnetized free layer and an in-plane magnetized reference layer is comprehensively studied theoretically. A forced synchronization by the alternating current is observed in numerical simulation over wide ranges of its amplitude and frequency. An analytical theory clarifies that the nonlinear frequency shift, as well as the spin-transfer torque asymmetry, plays a key role in determining locking range and phase difference between the oscillator and current. Chaos caused by the alternating current is identified for a region of large alternating current by evaluating the Lyapunov exponent. Similar results are also obtained for microwave field, although the parameter regions causing chaos are narrower than those by the alternating current.

cond-mat.mes-hall↗

arXiv2019

Chaos in nanomagnet via feedback current

Nonlinear magnetization dynamics excited by spin-transfer effect with feedback current is studied both numerically and analytically. The numerical simulation of the Landau-Lifshitz-Gilbert equation indicates the positive Lyapunov exponent for a certain range of the feedback rate, which identifies the existence of chaos in a nanostructured ferromagnet. Transient behavior from chaotic to steady oscillation is also observed in another range of the feedback parameter. An analytical theory is also developed, which indicates the appearance of multiple attractors in a phase space due to the feedback current. An instantaneous imbalance between the spin-transfer torque and damping torque causes a transition between the attractors, and results in the complex dynamics.

cond-mat.mes-hall↗