Results 141 to 150 of about 7,839,223 (287)

Light SDI-NAS: Lightweight Convolutional Neural Networks for Surface Defect Segmentation Based on Neural Architecture Search

Applied Sciences
Convolutional neural networks (CNNs) have achieved remarkable performance in industrial image-based surface defect inspection in recent years. However, many state-of-the-art (SOTA) networks have become increasingly complex and computationally expensive ...
Qingshi Chen, Biao Chen, Xianshi Jia, Kai Li   +3 more
doaj   +1 more source

Mutual Adaptation and Influence: Review of Latent Dynamics Models in Human–Robot Interaction

Advanced Robotics Research, EarlyView.
Robots are becoming better teammates by learning hidden patterns in how people act. This review covers how state‐of‐the‐art approaches leverage these patterns to help robots not only react but also anticipate and guide cooperation. Here, we synthesize a unifying framework for these approaches, classify and review existing works, and highlight key ...
Mason O. Smith, Sunny Amatya, Seyed Yousef Soltanian, Jonathan Bush, Wenlong Zhang   +4 more
wiley   +1 more source

Delta-NAS: Difference of Architecture Encoding for Predictor-Based Evolutionary Neural Architecture Search

2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Neural Architecture Search (NAS) continues to serve a key roll in the design and development of neural networks for task specific deployment. Modern NAS techniques struggle to deal with ever increasing search space complexity and compute cost constraints.
Arjun Sridhar, Yiran Chen 0001
openaire   +2 more sources

NAS-SpatialFlow : neural architecture search for panoptic segmentation

, 2020
Neural architecture search (NAS) has achieved success in various deep learning tasks. NAS can automatically find an efficient neural network architecture for a certain task on a dataset, which can outperform human-designed neural architectures.
Cao, Liu
core  

MicroRoboScope: A Portable and Integrated Mechatronic Platform for Magnetic and Acoustic Microrobotic Experimentation

Advanced Robotics Research, EarlyView.
This work presents the MicroRoboScope, a highly integrated, compact, and portable microrobotic experimentation platform combining electromagnetic and acoustic actuation with real‐time visual feedback into a single, end‐to‐end device. The system enables closed‐loop control and tracking algorithm experimentation within an accessible and unified hardware ...
Max Sokolich, Yanda Yang, Subrahmanyam Cherukumilli, Fatma Ceren Kirmizitas, Sambeeta Das   +4 more
wiley   +1 more source

DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification

, 2023
Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture, nor encodes the latent hierarchical ...
Lee, Kuo-Jung, Li, Cheng-Te, Chen, Kuan-Chun   +2 more
core  

From Lab to Landscape: Environmental Biohybrid Robotics for Ecological Futures

Advanced Robotics Research, EarlyView.
This Perspective explores environmental biohybrid robotics, integrating living tissues, microorganisms, and insects for operation in real‐world ecosystems. It traces the leap from laboratory experiments to forests, wetlands, and urban environments and discusses key challenges, development pathways, and opportunities for ecological monitoring and ...
Miriam Filippi
wiley   +1 more source

Task‐Oriented Path Planning Towards Autonomous Sensor Network Deployment in Rainforest Canopies

Advanced Robotics Research, EarlyView.
An informative path planner for drone‐based deployment of wireless sensor networks in rainforest canopies is presented, addressing key challenges in large‐scale biodiversity monitoring. By integrating canopy surface detection with connectivity‐aware sampling under strict flight constraints, the approach enables efficient and reliable aerial sensor ...
Rita Santos Raminhos, Salua Hamaza
wiley   +1 more source

A graph neural architecture search approach for identifying bots in social media

Frontiers in Artificial Intelligence
Social media platforms, including X, Facebook, and Instagram, host millions of daily users, giving rise to bots automated programs disseminating misinformation and ideologies with tangible real-world consequences.
Georgios Tzoumanekas, Michail Chatzianastasis, Loukas Ilias, George Kiokes, John Psarras, Dimitris Askounis   +5 more
doaj   +1 more source

DRIVE‐SAFE: Data‐Driven Robustness and Informed Validation for Evolving Specifications via Formal Evaluation

Advanced Robotics Research, EarlyView.
DRIVE‐SAFE evaluates learning‐based, black‐box autonomous driving policies against evolving temporal safety requirements using Signal Temporal Logic robustness metrics. It aggregates distributional robustness measures with domain‐informed weights to guide iterative retraining.
Kristy Sakano, Jianyu An, Dinesh Manocha, Huan Xu   +3 more
wiley   +1 more source