14 citations · 42 across the 21 of their papers we have counts for
22 papers
Context-dependent time-series prediction via HyperReservoirs
Kohei Tsuchiyama, Takatomo Mihana, Ryoichi Horisaki +1
Time series prediction is a common application of reservoir computing. When the training and testing time series data contains multiple dynamical regimes, because an underlying par…
Reconstructing the information processing capacity of physical systems from noisy observations
Shun Kotoku, Rodrigo Martínez-Peña, Takatomo Mihana +5
Driven dynamical systems can compute when their transient states encode complex transformations of past inputs. The information processing capacity (IPC) framework allows for a det…
Autocorrelation effects in a stochastic-process model for solving two-armed bandit problems
Tomoki Yamagami, Mikio Hasegawa, Takatomo Mihana +2
Decision makers exploiting photonic chaotic dynamics obtained by semiconductor lasers provide an ultrafast approach to solving multi-armed bandit problems by using a temporal optic…
Time-multiplexed layer reuse for physical neural networks
Kohei Tsuchiyama, Andre Roehm, Takatomo Mihana +1
Physical neural networks (PNNs) are promising candidates for next-generation computing, but existing demonstrations remain several orders of magnitude smaller than modern digital n…
Photonic decision making using optical frequency difference detection in mutually-coupled semiconductor lasers
Hidetoshi Taira, Takatomo Mihana, Shun Kotoku +4
As electronic computing approaches its performance limits, photonic accelerators have emerged as promising alternatives. Photonic accelerators exploiting semiconductor-laser synchr…
Quantum spatial best-arm identification via quantum walks
Tomoki Yamagami, Etsuo Segawa, Takatomo Mihana +3
Quantum reinforcement learning has emerged as a framework combining quantum computation with sequential decision-making, and applications to the multi-armed bandit (MAB) problem ha…
Multi-player conflict avoidance through entangled quantum walks
Honoka Shiratori, Tomoki Yamagami, Etsuo Segawa +3
Quantum computing has the potential to solve complex problems faster and more efficiently than classical computing. It can achieve speedups by leveraging quantum phenomena like sup…
Scalable Conflict-free Decision Making with Photons
Kohei Konaka, André Röhm, Takatomo Mihana +1
Quantum optics utilizes the unique properties of light for computation or communication. In this work, we explore its ability to solve certain reinforcement learning tasks, with a…
Decentralized multi-agent reinforcement learning algorithm using a cluster-synchronized laser network
Shun Kotoku, Takatomo Mihana, André Röhm +1
Multi-agent reinforcement learning (MARL) studies crucial principles that are applicable to a variety of fields, including wireless networking and autonomous driving. We propose a…
Experimental control of mode-competition dynamics in a chaotic multimode semiconductor laser for decision making
Ryugo Iwami, Takatomo Mihana, Kazutaka Kanno +2
Photonic computing has been widely used to accelerate the computational performance in machine learning. Photonic decision-making is a promising approach that uses photonic computi…
Asymmetric leader-laggard cluster synchronization for collective decision-making with laser network
Shun Kotoku, Takatomo Mihana, André Röhm +2
Photonic accelerators have recently attracted soaring interest, harnessing the ultimate nature of light for information processing. Collective decision-making with a laser network,…
Conflict-free joint decision by lag and zero-lag synchronization in laser network
Hisako Ito, Takatomo Mihana, Ryoichi Horisaki +1
With the end of Moore's Law and the increasing demand for computing, photonic accelerators are garnering considerable attention. This is due to the physical characteristics of ligh…
Bandit Algorithm Driven by a Classical Random Walk and a Quantum Walk
Tomoki Yamagami, Etsuo Segawa, Takatomo Mihana +3
Quantum walks (QWs) have a property that classical random walks (RWs) do not possess -- the coexistence of linear spreading and localization -- and this property is utilized to imp…
Effect of temporal resolution on the reproduction of chaotic dynamics via reservoir computing
Kohei Tsuchiyama, André Röhm, Takatomo Mihana +2
Reservoir computing is a machine learning paradigm that uses a structure called a reservoir, which has nonlinearities and short-term memory. In recent years, reservoir computing ha…
Information-theoretical analysis of statistical measures for multiscale dynamics
Naoki Asuke, Tomoki Yamagami, Takatomo Mihana +3
Multiscale entropy (MSE) has been widely used to examine nonlinear systems involving multiple time scales, such as biological and economic systems. Conversely, Allan variance has b…
Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation
Hiroaki Shinkawa, Nicolas Chauvet, André Röhm +4
Recently, extensive studies on photonic reinforcement learning to accelerate the process of calculation by exploiting the physical nature of light have been conducted. Previous stu…
Pairing optimization via statistics: Algebraic structure in pairing problems and its application to performance enhancement
Naoki Fujita, André Röhm, Takatomo Mihana +4
Fully pairing all elements of a set while attempting to maximize the total benefit is a combinatorically difficult problem. Such pairing problems naturally appear in various situat…
Parallel photonic accelerator for decision making using optical spatiotemporal chaos
Kensei Morijiri, Kento Takehana, Takatomo Mihana +3
Photonic accelerators have attracted increasing attention in artificial intelligence applications. The multi-armed bandit problem is a fundamental problem of decision making using…
Skeleton structure inherent in discrete-time quantum walks
Tomoki Yamagami, Etsuo Segawa, Ken'ichiro Tanaka +4
In this paper, we claim that a common underlying structure--a skeleton structure--is present behind discrete-time quantum walks (QWs) on a one-dimensional lattice with a homogeneou…
Conflict-free joint sampling for preference satisfaction through quantum interference
Hiroaki Shinkawa, Nicolas Chauvet, André Röhm +4
Collective decision-making is vital for recent information and communications technologies. In our previous research, we mathematically derived conflict-free joint decision-making…
Controlling chaotic itinerancy in laser dynamics for reinforcement learning
Ryugo Iwami, Takatomo Mihana, Kazutaka Kanno +3
Photonic artificial intelligence has attracted considerable interest in accelerating machine learning; however, the unique optical properties have not been fully utilized for achie…
Scalable photonic reinforcement learning by time-division multiplexing of laser chaos
Makoto Naruse, Takatomo Mihana, Hirokazu Hori +4
Reinforcement learning involves decision making in dynamic and uncertain environments and constitutes a crucial element of artificial intelligence. In our previous work, we experim…