Results 171 to 180 of about 117,293 (275)

Hybrid lightweight vision transformers with attention mechanism for feature extraction and classification of product designs. [PDF]

PLoS One
Wahid A, Khan HU, Naz A, Alarfaj FK.
europepmc   +1 more source

Double‐Integration‐Enhanced Stochastic Gradient Descent Based on Neural Dynamics for Improving Generalisation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Generalisation is a crucial aspect of deep learning, enabling models to perform well on unseen data. Currently, most optimisers that improve generalisation typically suffer from efficiency bottlenecks. This paper proposes a double‐integration‐enhanced stochastic gradient descent (DIESGD) optimiser, which treats the negative gradient as an ...
Ting Li, Longbang Wang, Jiexing Li, Jicheng Li   +3 more
wiley   +1 more source

Lightweight Deep Learning for Automated Dental Caries Screening from Pediatric Oral Photographs. [PDF]

Diagnostics (Basel)
Alangari N, AlShenaifi N.
europepmc   +1 more source

CDFNet: Cross‐Modal Deep Fusion for Monocular 3D Semantic Scene Completion

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Semantic scene completion (SSC) aims to predict the semantic occupancy and geometry of 3D scenes. Recently, most studies focus on camera‐based approaches due to the rich visual cues of images and the cost‐effectiveness of cameras. However, these methods usually lack efficient fusion and fine‐grained processing of cross‐modal semantic ...
Xianjing Cheng, Lintai Wu, Jie Wen, Tianhao Peng, Yong Xu, Zairong Wei   +5 more
wiley   +1 more source

A Cattle Behavior Recognition Method Based on Graph Neural Network Compression on the Edge. [PDF]

Animals (Basel)
Liu H, Song P, Xin X, Rong Y, Gao J, Wang Z, Zhang Y.   +6 more
europepmc   +1 more source

Vertical Deformation Mapping: Steering Optimiser Toward Flat Minima

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Standard deep learning optimisation is typically conducted on shape‐fixed loss surfaces. However, shape‐fixed loss surfaces may impede optimisers from reaching flat regions closely associated with strong generalisation. In this work, we propose a new paradigm named deformation mapping to deform the loss surface during optimisation.
Liangming Chen, Longbang Wang, Man‐Fai Leung, Jianfeng Li, Long Jin   +4 more
wiley   +1 more source

ResNet based backbone integrated YOLO framework for bone fracture detection. [PDF]

Sci Rep
Bhattacharya D, Das S, Biswas T, Mandal G.   +3 more
europepmc   +1 more source

Neural Network Repair With Shapley‐Guided Search

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT The deployment of deep neural networks (DNNs) in safety‐critical domains is critically hampered by their vulnerability to defects, which can arise from malicious attacks or low‐quality data. Therefore, precisely locating the network components responsible for these defects, and subsequently repairing them without compromising overall model ...
Xiaofu Du, Zixiong Zhang, Xuesong Wang, Linqiang Liu, Junyan Qian   +4 more
wiley   +1 more source

A multi-scale hybrid ResNet-transformer with distance-aware learning for interpretable BI-RADS mammographic classification. [PDF]

Sci Rep
Singh M, Mohan A, Tripathi U, Pathak S, Gupta R, Kumar B.   +5 more
europepmc   +1 more source

Classification of Broadband Oscillations Using Wavelet Convolution and Multi‐Channel Attention Network

Energy Internet, EarlyView.
ABSTRACT Accurate identification of broadband oscillation types is a prerequisite for implementing appropriate control strategies. The strongly nonlinear, nonstationary and multi‐modal characteristics of broadband oscillation signals impose higher demands on identification methods. Practical applications face challenges such as coupling effects between
Jinduo Yang, Ji Li, Yiyan Li, Yang Gao, Qingyuan Zhang, Yang Kou, Xiao Hu, WeiLe Liang   +7 more
wiley   +1 more source