Results 111 to 120 of about 7,097,220 (297)

Learning the Kernel with Hyperkernels.

open access: yesJ. Mach. Learn. Res., 2005
This paper addresses the problem of choosing a kernel suitable for estimation with a Support Vector Machine, hence further automating machine learning. This goal is achieved by defining a Reproducing Kernel Hilbert Space on the space of kernels itself.
Ong, Cheng Soon   +2 more
openaire   +3 more sources

Intelligent Maintenance Review for Robots: Multimodal Information, Deep Diagnosis and Embodied Artificial Intelligence

open access: yesAdvanced Robotics Research, EarlyView.
This review maps the methods to monitor robots’ health by fusing vibration, sound, control signals, vision, force, and oil information with artificial intelligence. It identifies deep learning, transfer learning, digital twins, and physics‐informed models as key methodological pathways enabling earlier diagnosis, safer human–robot collaboration, and ...
Yuting Qiao   +6 more
wiley   +1 more source

Bayesian Learning of Kernel Embeddings

open access: yes, 2016
Conference paper appearing in UAI 2016, including ...
Filippi, S   +3 more
openaire   +4 more sources

Autonomous Navigation of Pollen‐Inspired Magnetic Microrobots for Biomedical Applications

open access: yesAdvanced Robotics Research, EarlyView.
A sunflower pollen‐inspired magnetic microrobot enables controlled rolling navigation in vessel‐like environments. Its open geometry reduces hydrodynamic drag, while vision‐based closed‐loop control, shortest‐path planning, and reinforcement learning support target‐reaching and maze navigation with microrobot‐scale accuracy, highlighting a route toward
Ali Anil Demircali   +6 more
wiley   +1 more source

Flexible Sensors for Robotics Tactile Perception: A Review

open access: yesAdvanced Robotics Research, EarlyView.
Flexible tactile sensing for robotics is reviewed through four interconnected dimensions. Physical mechanisms include piezoresistive, capacitive, piezoelectric, triboelectric, iontronic, and optical sensing. Structural design includes bioinspired, defect‐based, and MEMS‐based tactile systems.
Yu Song, Ying Chen, Yihao Chen, Xue Feng
wiley   +1 more source

Basic metric learning

open access: yes, 2008
This report presents a a novel Multiple Kernel Learning (MKL) algorithm for the 1-class support vector machine. The emphasis is placed on viewing the CBIR task with relevance feedback as a metric learning problem, where each image has 11 different ...
Hussain, Zakria   +3 more
core   +1 more source

UC Food Waste: A Multimodal Robotic Perception Dataset for Robust Contaminant Detection in Complex Biowaste Scenes

open access: yesAdvanced Robotics Research, EarlyView.
A balanced multimodal food‐waste dataset and a novel Split Spatial‐Spectral Attention fusion framework are presented for robotic contaminant detection. Separate processing of RGB, thermal, and multispectral inputs preserves subtle material signatures before feature integration, reducing modality interference and improving classification and ...
Matthew Vestal   +5 more
wiley   +1 more source

Enhancing Amphibious Flipper‐Based Locomotion Through Terrain‐Dependent Bayesian Optimization of Central Pattern Generator Control

open access: yesAdvanced Robotics Research, EarlyView.
A sea turtle‐inspired amphibious robot uses simulation‐guided optimization to adapt its flipper coordination to different environments. Sensitivity analysis and multiobjective Bayesian optimization identify terrain‐dependent controllers that are validated on hardware.
Nnamdi C. Chikere, Yasemin Ozkan‐Aydin
wiley   +1 more source

Model Predictive Control for Magnetically Actuated Cellbots

open access: yesAdvanced Robotics Research, EarlyView.
Magnetically actuated cellbots, formed by embedding microrobots in living cells, are steered along precise paths using a model predictive controller enhanced with a Gaussian process disturbance estimator. The data‐efficient method calibrates each cellbot individually, cutting modeling error by roughly 60% and enabling accurate navigation through cell ...
Mehdi Kermanshah   +8 more
wiley   +1 more source

Neural Fields for Highly Accelerated 2D Cine Phase Contrast MRI

open access: yesAdvanced Science, EarlyView.
ABSTRACT 2D cine phase contrast (CPC) MRI provides quantitative information on blood velocity and flow within the human vasculature. However, data acquisition is time‐consuming, motivating the reconstruction of the velocity field from undersampled measurements to reduce scan times. In this work, neural fields are proposed as a continuous spatiotemporal
Pablo Arratia   +7 more
wiley   +1 more source

Home - About - Disclaimer - Privacy