Asymmetric leader-laggard cluster synchronization for collective decision-making with laser network

• URL: http://arxiv.org/abs/2312.02537v1
• Date: Tue, 5 Dec 2023 07:04:21 GMT
• Title: Asymmetric leader-laggard cluster synchronization for collective decision-making with laser network
• Authors: Shun Kotoku, Takatomo Mihana, Andr\'e R\"ohm, Ryoichi Horisaki, and Makoto Naruse
• Abstract summary: Photonic accelerators have attracted soaring interest, harnessing the ultimate nature of light for information processing. Our study highlights the capability and significance of machine learning built upon chaotic lasers and photonic devices.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Photonic accelerators have recently attracted soaring interest, harnessing the ultimate nature of light for information processing. Collective decision-making with a laser network, employing the chaotic and synchronous dynamics of optically interconnected lasers to address the competitive multi-armed bandit (CMAB) problem, is a highly compelling approach due to its scalability and experimental feasibility. We investigated essential network structures for collective decision-making through quantitative stability analysis. Moreover, we demonstrated the asymmetric preferences of players in the CMAB problem, extending its functionality to more practical applications. Our study highlights the capability and significance of machine learning built upon chaotic lasers and photonic devices.

Related papers

• Wireless Human-Machine Collaboration in Industry 5.0 [75.78721184383897]
  Wireless Human-Machine Collaboration represents a critical advancement for Industry 5.0. Stability analysis certifies how the closed-loop system will behave under model randomness. This paper establishes a fundamental WHMC model incorporating dual wireless loops for machine and human control.
  arXiv  Detail & Related papers  (2024-10-18T03:44:10Z)
• Decentralized multi-agent reinforcement learning algorithm using a cluster-synchronized laser network [1.124958340749622]
  We propose a photonic-based decision-making algorithm to address the competitive multi-armed bandit problem. Our numerical simulations demonstrate that chaotic oscillations and cluster synchronization of optically coupled lasers, along with our proposed decentralized coupling adjustment, efficiently balance exploration and exploitation.
  arXiv  Detail & Related papers  (2024-07-12T09:38:47Z)
• Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control [63.310780486820796]
  We show how a parameterization of recurrent connectivity influences robustness in closed-loop settings. We find that closed-form continuous-time neural networks (CfCs) with fewer parameters can outperform their full-rank, fully-connected counterparts.
  arXiv  Detail & Related papers  (2023-10-05T21:44:18Z)
• Conflict-free joint decision by lag and zero-lag synchronization in laser network [0.0]
  In this study, we explore the application of a laser network, acting as a photonic accelerator, to the competitive multi-armed bandit problem. We experimentally demonstrate cooperative decision-making using zero-lag and lag synchronization within a network of four semiconductor lasers.
  arXiv  Detail & Related papers  (2023-07-28T07:45:44Z)
• Deep Learning and Image Super-Resolution-Guided Beam and Power Allocation for mmWave Networks [80.37827344656048]
  We develop a deep learning (DL)-guided hybrid beam and power allocation approach for millimeter-wave (mmWave) networks. We exploit the synergy of supervised learning and super-resolution technology to enable low-overhead beam- and power allocation.
  arXiv  Detail & Related papers  (2023-05-08T05:40:54Z)
• Decision-making and control with diffractive optical networks [1.3356127774729136]
  The ultimate goal of artificial intelligence is to mimic the human brain to perform decision-making and control directly from high-dimensional sensory input. Diffractive optical networks provide a promising solution for implementing artificial intelligence with high-speed and low-power consumption. Here, we propose using deep reinforcement learning to implement diffractive optical networks that imitate human-level decision-making and control capability.
  arXiv  Detail & Related papers  (2022-12-21T14:39:52Z)
• Predictive GAN-powered Multi-Objective Optimization for Hybrid Federated Split Learning [56.125720497163684]
  We propose a hybrid federated split learning framework in wireless networks. We design a parallel computing scheme for model splitting without label sharing, and theoretically analyze the influence of the delayed gradient caused by the scheme on the convergence speed.
  arXiv  Detail & Related papers  (2022-09-02T10:29:56Z)
• Controlling chaotic itinerancy in laser dynamics for reinforcement learning [0.0]
  Chaotic itinerancy can be employed to realize brain-like functionalities. We propose a method for controlling the chaotic itinerancy in a multi-mode semiconductor laser to solve a machine learning task.
  arXiv  Detail & Related papers  (2022-05-12T09:48:43Z)
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images [82.1679766706423]
  Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. We propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs. Our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2021-10-27T07:18:32Z)
• Joint Deep Reinforcement Learning and Unfolding: Beam Selection and Precoding for mmWave Multiuser MIMO with Lens Arrays [54.43962058166702]
  millimeter wave (mmWave) multiuser multiple-input multiple-output (MU-MIMO) systems with discrete lens arrays have received great attention. In this work, we investigate the joint design of a beam precoding matrix for mmWave MU-MIMO systems with DLA.
  arXiv  Detail & Related papers  (2021-01-05T03:55:04Z)
• Bandwidth-Adaptive Feature Sharing for Cooperative LIDAR Object Detection [2.064612766965483]
  Situational awareness as a necessity in the connected and autonomous vehicles (CAV) domain. Cooperative mechanisms have provided a solution to improve situational awareness by utilizing high speed wireless vehicular networks. We propose a mechanism to add flexibility in adapting to communication channel capacity and a novel decentralized shared data alignment method.
  arXiv  Detail & Related papers  (2020-10-22T00:12:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.