이 연구는 다중 끌개를 가진 시스템의 동역학을 효과적으로 모델링하기 위해 시간 지연 비선형 맵과 위상 공간 정보를 활용한 데이터 기반 시스템 식별 알고리즘(NLDM)을 제시합니다.
This paper introduces a novel data-driven method called Nonlinear Delayed Maps (NLDM) for identifying nonlinear dynamical systems, particularly those with multiple attractors, by leveraging time-delayed states and nonlinear feature mappings to improve prediction accuracy across different regions of the phase space.
本稿では、Infomapを用いた階層的なコミュニティ検出手法を都市部のオンデマンド配送ネットワークに適用することで、配送効率の向上を実現する多層的な管理フレームワークを提案しています。
Deep learning, particularly transformer networks, revolutionizes heavy particle identification in particle physics by effectively analyzing complex jet data, surpassing traditional methods in accuracy and scalability.
This review explores the intriguing connection between stochastic quantization in physics and diffusion models in machine learning, highlighting their shared mathematical framework based on stochastic differential equations (SDEs) and their potential for mutually beneficial applications.
本文介紹了 2024 年開放催化劑實驗 (OCx24) 數據集,該數據集結合大規模實驗和計算篩選,以構建預測模型,用於加速發現綠色氫氣生產和二氧化碳升級回收的催化劑,特別強調了數據驅動方法在識別有前景的氫析出反應 (HER) 催化劑方面的能力。
본 논문에서는 대규모 실험 데이터 세트인 OCx24를 통해 머신러닝 모델을 활용하여 촉매 발견을 가속화하고 계산 모델과 실험 결과 사이의 차이를 해소하는 방법을 제시합니다.
大規模な実験データセットと計算モデルを組み合わせることで、グリーン水素製造やCO2アップサイクリングに不可欠な、低コストで耐久性があり、効果的な触媒の発見を加速できる。
The OCx24 project leverages a large-scale experimental dataset and computational modeling to bridge the gap between theoretical predictions and real-world performance of catalysts for green hydrogen production and CO2 upcycling.
本研究利用原子特定持久同源性方法,將層狀混合鹵化鉛的拓撲結構編碼成條形碼,並結合梯度提升樹模型,成功預測了材料的能帶隙,證明了拓撲表示法在機器學習材料設計中的潛力。