613 citations
- The University of TokyoJP226 papers
- Kyoto UniversityJP134 papers
- High Energy Accelerator Research OrganizationJP109 papers
- Kavli Institute for the Physics and Mathematics of the UniverseJP104 papers
- Institute for Cosmic Ray ResearchJP97 papers
- Kobe UniversityJP87 papers
- Nagoya UniversityJP86 papers
- Tokyo Institute of TechnologyJP79 papers
- Miyagi University of EducationJP77 papers
- Centre National de la Recherche ScientifiqueFR76 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di PadovaIT76 papers
- Tohoku UniversityJP71 papers
671 papers
Odd-Parity Crystalline Electric Field and Multipoles in Icosahedral Quasicrystal and Approximant: Magnetic Toroidal and Electric Dipoles in Ce-Based Systems
Shinji Watanabe, Syunta Furuya, Mitsuaki Kawamura
Quasicrystals (QCs) lack periodic arrangement of atoms but possess unique structural order distinct from periodic crystals and random systems. The electronic property is far from c…
Kolmogorov-Arnold Classifier Systems as Universal Approximators
Hiroki Shiraishi, Hisao Ishibuchi, Masaya Nakata
As the input dimension grows, rule-based machine learning, such as Learning Classifier Systems (LCSs), faces a fundamental scalability bottleneck for function approximation: bo…
Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition
Yuta Kurotaki, Shusuke Yamakoshi, Reitaro Yoshida +6
Silent speech recognition (SSR) provides an alternative communication pathway in the absence of audible speech. However, conventional approaches are limited by the need for constan…
An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models
Kei Nishihara, Yaochu Jin, Masaya Nakata
An ensemble of surrogate models helps improve the prediction quality and robustness of surrogate models, and in turn, the search performance of surrogate-assisted evolutionary algo…
Neural Architecture Search of Sample Reweighting Networks for Complex Distribution Shift
Keisuke Sugawara, Kento Uchida, Shinichi Shirakawa
Sample reweighting is a major approach to addressing distribution shifts, such as label noise and class imbalance. Meta-Weight-Net (MW-Net) is a promising sample reweighting networ…
Weight Adaptation for Improving Parallel Performance of Adaptive Stochastic Natural Gradient
Yutaro Yamada, Kento Uchida, Shinichi Shirakawa
Probabilistic model-based evolutionary algorithms are promising for black-box optimization. Specifically, the adaptive stochastic natural gradient (ASNG) adaptively updates its lea…