Results 121 to 130 of about 9,834 (275)

Reliable Intelligent Diagnostics With Uncertainty Quantification for Mechanical System Condition Assessment

Quality and Reliability Engineering International, EarlyView.
ABSTRACT Health condition assessment of mechanical systems is essential to ensure their safe and reliable operation. Although AI‐driven diagnostic techniques have advanced significantly with the development of deep learning, the reliability of such techniques is often compromised due to the lack of uncertainty quantification (UQ)—particularly the ...
Guangjun Jiang, Haotian Ouyang, Zifei Xu
wiley   +1 more source

Vector Quantization Prompting for Continual Learning

Advances in Neural Information Processing Systems 37
Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i.e., prompts) to encode task knowledge, from which appropriate ones are selected to guide the fixed pre-trained model in generating ...
Li Jiao, Qiuxia Lai, Yu Li 0007, Qiang Xu 0001   +3 more
openaire   +3 more sources

Control System for the Navigation of the Agricultural Robots: A Review

Journal of Field Robotics, EarlyView.
ABSTRACT Control systems for the navigation of autonomous agricultural robots—particularly those operating in uneven terrain and in the presence of static or dynamic obstacles—have advanced considerably in recent years. As conventional machinery evolves toward increasingly automated systems, the design of reliable navigation controllers has become ...
Edna Carolina Moriones Polanía, Hugo Rafacho Fernandes, Daniel Albiero, Angel Pontin Garcia   +3 more
wiley   +1 more source

UVeQFed: Universal Vector Quantization for Federated Learning

, 2020
Traditional deep learning models are trained at a centralized server using data samples collected from users. Such data samples often include private information, which the users may not be willing to share.
Shlezinger, Nir, Chen, Mingzhe, Eldar, Yonina C, Poor, H Vincent, Cui, Shuguang   +4 more
core   +1 more source

Pyramid Vector Quantization for Deep Learning

CoRR, 2017
This paper explores the use of Pyramid Vector Quantization (PVQ) to reduce the computational cost for a variety of neural networks (NNs) while, at the same time, compressing the weights that describe them. This is based on the fact that the dot product between an N dimensional vector of real numbers and an N dimensional PVQ vector can be calculated ...
openaire   +2 more sources

Low‐Complexity Hybrid Beamforming for LEO Satellites: Beam Update Rate Analysis and Advanced Adaptive Precoding

International Journal of Satellite Communications and Networking, EarlyView.
ABSTRACT Low Earth Orbit (LEO) satellite constellations offer unprecedented opportunities for global broadband connectivity but pose significant beamforming challenges due to rapid platform motion and stringent onboard hardware constraints. Fully digital architectures, while optimal in theory, remain impractical for satellite payloads, motivating ...
Mohammad Momani, Thomas Delamotte, Andreas Knopp   +2 more
wiley   +1 more source

A state evaluation and fault diagnosis strategy for substation relay protection system integrating multiple intelligent algorithms

The Journal of Engineering
Ensuring the operational reliability of substation relay protection systems through rapid defect diagnosis and state assessment is crucial for maintaining power system stability.
Jiajun Wang, Shiyi Jing, Yu Yao, Kunlun Wang, Bo Li   +4 more
doaj   +1 more source

Brain‐Inspired Neuromorphic Device for Artificial Intelligent Robots Applications

SmartBot, EarlyView.
Brain‐inspired neuromorphic devices mimic biological systems to provide an efficient hardware foundation for embodied intelligent robotics. This review explores the material systems and corresponding computing architectures of neuromorphic devices that support low‐power perception, adaptive learning, and real‐time decision‐making.
Jiachen Han, Zheng Wang, Tianyu Wang, Jialin Meng   +3 more
wiley   +1 more source

Sparse approximations for kernel learning vector quantization

, 2013
Hofmann D, Hammer B. Sparse approximations for kernel learning vector quantization.
Hofmann, Daniela, Hammer, Barbara ; https://orcid.org/   +1 more
core  

A Bilayer Rare‐Earth/High‐κ Oxide Memristor for Energy‐Efficient Neuromorphic Intelligence

Small, EarlyView.
Interface‐engineered Gd2O3/HfO2 bilayer memristors demonstrate controlled filament formation, ultralow switching energy (∼13.56 pJ), and fast operation (∼350 ns) with a high ON/OFF ratio (∼107). The devices exhibit stable analog synaptic behavior and enable pattern recognition on Fashion‐MNIST, underscoring their promise for energy‐efficient ...
Hammad Ghazanfar, Muhammad Rabeel, Honggyun Kim, Sobia Nisar, Muhammad Wajid Zulfiqar, Muneeb Ahmad, Rana Faryad Ali, Ghulam Dastgeer, Deok‐kee Kim   +8 more
wiley   +1 more source