Results 131 to 140 of about 75,461 (296)
Advanced Materials Technologies, EarlyView.Transducers convert physical signals into electrical and optical representations, yet each mechanism is bounded by intrinsic trade‐offs across bandwidth, sensitivity, speed, and energy. This review maps transduction mechanisms across physical scale and frequency, showing how heterogeneous integration and multiphysics co‐design transform isolated ...
Aolei Xu +8 more
wiley +1 more source
Advanced Materials Technologies, EarlyView.This article highlights the development of robust and high‐performance flexible and stretchable biosensors that maintain long‐term functionality and optimal electrical conductivity under mechanical deformation, utilizing sustainable and cost‐effective manufacturing principles.
Mousa H. Aldosari, Ahyeon Koh
wiley +1 more source
Data‐Efficient Electromagnetic Surrogate Solver Through Dissipative Relaxation Transfer Learning
Advanced Optical Materials, EarlyView.Dissipative relaxation transfer learning (DIRTL) enables data‐efficient training of electromagnetic surrogate solvers by pretraining data generated with artificial material loss before fine‐tuning on target lossless data. The framework suppresses resonant outlier effects during early training, allowing effective adaptation to high‐amplitude resonances ...
Sunghyun Nam +2 more
wiley +1 more source
Machine Learning Enables Inverse Design of Optically Driven Microscopic Metavehicles
Advanced Optical Materials, EarlyView.Machine‐learning‐based inverse design is used optimize “metavehicles” — flat microparticles based on metagratings that generate a strong lateral optical force from normally incident light. The optimized design exhibits a force efficiency of ∼88% and a measured propulsion speed in water much higher than previously reported, demonstrating that inverse ...
Vasilii Mylnikov +2 more
wiley +1 more source
Stable Imitation of Multigait and Bipedal Motions for Quadrupedal Robots Over Uneven Terrains
Advanced Robotics Research, EarlyView.How are quadrupedal robots empowered to execute complex navigation tasks, including multigait and bipedal motions? Challenges in stability and real‐world adaptation persist, especially with uneven terrains and disturbances. This article presents an imitation learning framework that enhances adaptability and robustness by incorporating long short‐term ...
Erdong Xiao +3 more
wiley +1 more source
An Improved Search Economics for Convolutional Neural Network Architecture Search
, 2022 Designing an accurate convolutional neural network must construct different architectures and search corresponding hyperparameters according to the problem.
Chen, Yi-Ping
core
Collision‐Resilient Winged Drones Enabled by Tensegrity Structures
Advanced Robotics Research, EarlyView.Based on structures of birds such as the woodpeck, this article presents the collision‐resilient aerial robot, SWIFT. SWIFT leverages tensegrity structures in the fuselage and wings which allow it to undergo large deformations in a crash, without sustaining damage. Experiments show that SWIFT can reduce impact forces by 70% over conventional structures.
Omar Aloui +5 more
wiley +1 more source
Neural Architecture Search with Reinforcement Learning
CoRR, 2016 Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement ...
Barret Zoph, Quoc V. Le
openaire +3 more sources
Soft Robotic Snake with Tunable Undulatory Gait for Efficient Underwater Locomotion
Advanced Robotics Research, EarlyView.This study designs an underwater soft snake robot using 3D‐printed soft actuators, controlled by specific signals to generate sinusoidal undulation. Results show a positive correlation between speed and swing amplitude, with optimal performance at 2/3π phase offset, PLA tail, 1.2 voltage growth rate, and 6s undulation period achieving a maximum speed ...
Huichen Ma, Junjie Zhou, Raye Yeow
wiley +1 more source
Hardware-Aware Neural Architecture Search
319347The manual search for optimal neural network topologies, like maximizing the accuracy or minimizing the latency, is a time-consuming process that often requires multiple iterations. Depending on the use case, several target objectives are optimized
Loroch, Dominik
core +1 more source