6 papers
From Redundancy to Minimality: Fixed-Point-Guided Hierarchical Reduction of Learned Piecewise-Linear Dynamics
Hiroto Tamura, Gouhei Tanaka
Understanding a nonlinear dynamical system from time series requires not only reproducing its trajectories, but also identifying a simple representation that preserves its essentia…
Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Based Granular Ball Computing
Ziqiang Li, Yun Liu, Gouhei Tanaka
Dynamic Time Warping (DTW)-based Nearest-Neighbor (NN) classifiers are effective for time-series classification but are vulnerable to mislabeled training samples and require numero…
A Local Gauge-Covariant Formulation of Classical Dynamics
Gunjan Auti, Hirofumi Daiguji, Gouhei Tanaka
Classical dynamical laws are conventionally formulated as closed evolution equations defined on fixed geometric backgrounds and a global time parameter. We develop a formulation in…
Structuring Multiple Simple Cycle Reservoirs with Particle Swarm Optimization
Ziqiang Li, Robert Simon Fong, Kantaro Fujiwara +2
Reservoir Computing (RC) is a time-efficient computational paradigm derived from Recurrent Neural Networks (RNNs). The Simple Cycle Reservoir (SCR) is an RC model that stands out f…
Predicting unobserved climate time series data at distant areas via spatial correlation using reservoir computing
Shihori Koyama, Daisuke Inoue, Hiroaki Yoshida +2
Collecting time series data spatially distributed in many locations is often important for analyzing climate change and its impacts on ecosystems. However, comprehensive spatial da…
Diffusion model for relational inference
Shuhan Zheng, Ziqiang Li, Kantaro Fujiwara +1
Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interac…