Results 71 to 80 of about 98,895 (273)
AllReduce Scheduling with Hierarchical Deep Reinforcement Learning
AllReduce is a technique in distributed computing which saw use in many critical applications of deep learning. Existing methods of AllReduce scheduling oftentimes lack flexibility due to being topology-specific or relying on extensive handcrafted designs that require domain-specific knowledge.
Wei, Yufan, Liu, Mickel, Wu, Wenfei
openaire +2 more sources
Language as an Abstraction for Hierarchical Deep Reinforcement Learning
, 2019 Published in Neural Information Processing Systems (NeurIPS) 2019; Supplementary materials: https://sites.google.com/view/hal ...
Jiang, Yiding +3 more
openaire +2 more sources
Scalable Voltage Control using Structure-Driven Hierarchical Deep Reinforcement Learning
, 2021 8 pages, 13 ...
Mukherjee, Sayak +4 more
openaire +2 more sources
Advanced Healthcare Materials, EarlyView.This review explores how alternative invertebrate and small‐vertebrate models advance the evaluation of nanomaterials across medicine and environmental science. By bridging cellular and organismal levels, these models enable integrated assessment of toxicity, biodistribution, and therapeutic performance.
Marie Celine Lefevre +3 more
wiley +1 more source
The Path Planning of Mobile Robot by Neural Networks and Hierarchical Reinforcement Learning
Frontiers in Neurorobotics, 2020 Existing mobile robots cannot complete some functions. To solve these problems, which include autonomous learning in path planning, the slow convergence of path planning, and planned paths that are not smooth, it is possible to utilize neural networks to
Jinglun Yu, Yuancheng Su, Yifan Liao
doaj +1 more source
Advanced Materials, EarlyView.Metal‐free carbon catalysts enable the sustainable synthesis of hydrogen peroxide via two‐electron oxygen reduction; however, active site complexity continues to hinder reliable interpretation. This review critiques correlation‐based approaches and highlights the importance of orthogonal experimental designs, standardized catalyst passports ...
Dayu Zhu +3 more
wiley +1 more source
Recent Progress on Flexible Multimodal Sensors: Decoupling Strategies, Fabrication and Applications
Advanced Materials, EarlyView.In this review, we establish a tripartite decoupling framework for flexible multimodal sensors, which elucidates the underlying principles of signal crosstalk and their solutions through material design, structural engineering, and AI algorithms. We also demonstrate its potential applications across environmental monitoring, health monitoring, human ...
Tao Wu +10 more
wiley +1 more source
Advanced Materials Interfaces, EarlyView.SAA significantly enhanced Al/PU bonding, increasing SLSS by up to 920% and fracture energy by 15 100% through optimized micro‐nano porous surfaces. RSM identified the optimal anodizing conditions, while ML confirmed sulfuric acid concentration and roughness as dominant predictors of strength.
Umut Bakhbergen +6 more
wiley +1 more source
Strategies for Enhancing Thermal Conductivity of PDMS in Electronic Applications
Advanced Materials Technologies, EarlyView.This review explores effective strategies for enhancing heat dissipation in Polydimethylsiloxane (PDMS)‐based composites, focusing on particle optimization, 3D network design, and multifunctional integration. It offers key insights into cutting‐edge methods and simulations that are advancing thermal management in modern electronic devices.
Xiang Yan, Marisol Martin‐Gonzalez
wiley +1 more source
Deep Reinforcement Learning: A Chronological Overview and Methods
AIIntroduction: Deep reinforcement learning (deep RL) integrates the principles of reinforcement learning with deep neural networks, enabling agents to excel in diverse tasks ranging from playing board games such as Go and Chess to controlling robotic ...
Juan Terven
doaj +1 more source