Results 211 to 220 of about 212,585 (307)

Deviation‐Guided Attention for Semi‐Supervised Anomaly Detection With Contrastive Regularisation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Anomaly detection (AD) aims to identify abnormal patterns that deviate from normal behaviour, playing a critical role in applications such as industrial inspection, medical imaging and autonomous driving. However, AD often faces a scarcity of labelled data. To address this challenge, we propose a novel semi‐supervised anomaly detection method,
Guanglei Xie, Xiaochang Hu, Yi Sun, Wenzhuo Zhang, Yafeng Bu, Hao Fu, Xin Xu   +6 more
wiley   +1 more source

A hybrid recurrent neural network and optimization framework for intelligent mobile robot navigation in smart manufacturing. [PDF]

Sci Rep
Radha K, Karthikeyan S.
europepmc   +1 more source

Design and Validation of Zeroing Neural Network With Active Noise Rejection Capability for Time‐Varying Problems Solving

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Recently, the zeroing neural network (ZNN) has demonstrated remarkable effectiveness in tackling time‐varying problems, delivering robust performance across both noise‐free and noisy environments. However, existing ZNN models are limited in their ability to actively suppress noise, which constrains their robustness and precision in solving ...
Yilin Shang, Wenbo Zhang, Dongsheng Guo, Shan Xue   +3 more
wiley   +1 more source

Text-to-image generation with enhanced GANs: Bridging semantic gaps using RNN and CNN. [PDF]

PLoS One
Ramzan S, Ramzan HA, Kalsum T, Adnan M, Chaudhary MA, Ali MM.   +5 more
europepmc   +1 more source

Multi‐Objective Optimisation Framework for Heterogeneous Federated Learning

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server. Despite rapid progress, federated learning still faces several unsolved challenges. Specifically, communication costs and system heterogeneity, such as nonidentical data distribution,
Jamshid Tursunboev, Vikas Palakonda, Il‐Min Kim, Sunghwan Moon, Jae‐Mo Kang   +4 more
wiley   +1 more source

Online reinforcement learning of state representation in recurrent network supported by the power of random feedback and biological constraints. [PDF]

Elife
Tsurumi T, Kato A, Kumar A, Morita K.
europepmc   +1 more source

UNO: Unified Self‐Supervised Monocular Odometry for Platform‐Agnostic Deployment

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT This work presents UNO, a unified monocular visual odometry framework that enables robust and adaptable pose estimation across diverse environments, platforms and motion patterns. Unlike traditional methods that rely on deployment‐specific tuning or predefined motion priors, our approach generalises effectively across a wide range of real ...
Wentao Zhao, Yihe Niu, Yanbo Wang, Tianchen Deng, Shenghai Yuan, Zhenli Wang, Rui Guo, Jingchuan Wang   +7 more
wiley   +1 more source

Bioinspired Simultaneous Learning and Motion-Force Hybrid Control for Robotic Manipulators Under Multiple Constraints. [PDF]

Biomimetics (Basel)
Tong Y, Liu H, Zhang Z.
europepmc   +1 more source

TNCOA: Efficient Exploration via Observation‐Action Constraint on Trajectory‐Based Intrinsic Reward

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Efficient exploration is critical in handling sparse rewards and partial observability in deep reinforcement learning. However, most existing intrinsic reward methods based on novelty rely on single‐step observations or Euclidean distances.
Jingxiang Ma, Hongbin Ma, Youzhi Zhang
wiley   +1 more source

Carbon market price prediction in the Yangtze River Basin based on improved deep learning ensemble model with CEEMDAN and Attention-RNN. [PDF]

Carbon Balance Manag
Lu Z, Cao Z, Xiang Z, Li J, Li M.
europepmc   +1 more source