Results 121 to 130 of about 129,225 (287)

Deformable Attention Multiscale Feature Fusion Network‐Dehaze: An Adaptive Image Dehazing Method Based on Deformable Attention Multiscale Fusion Network

Advanced Intelligent Systems, EarlyView.
This paper presents the deformable attention multiscale feature fusion network‐dehaze adaptive image dehazing network, which integrates three core modules (revised residual shrinkage unit, multiscale attention, cross‐scale feature fusion). It incorporates deformable convolution and multiscale attention mechanisms to address the detail loss issue of ...
Ruipeng Wang, Yajun Chen, Hao Liu, Mingrui Li, Zhiqi Li   +4 more
wiley   +1 more source

Gate‐Align‐SED: Semi‐Supervised Sound Event Detection via Adaptive Feature Gating and Cross‐Task Alignment in Situation Awareness

Advanced Intelligent Systems, EarlyView.
Overview of the proposed Gate‐Align‐SED, including two stages of training: (1) Mean‐Teacher SSL Training; and (2) Enhancer Model Training. In complex real‐world environments such as disaster monitoring, effective sound event detection (SED) is often hindered by the presence of noise and limited labeled data.
Jieli Chen, Li‐Minn Ang, Chee Shen Lim, Kah Phooi Seng, Jeremy Smith   +4 more
wiley   +1 more source

The Cost of Avoiding Backpropagation

CoRR
Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization have been proposed as memory-efficient alternatives to backpropagation (BP) for gradient computation, especially in low-resource settings. However, their practical benefits remain unclear due to two key gaps: a lack of comparison against memory-efficient BP variants, such as
Kunjal Panchal, Sunav Choudhary, Yuriy Brun, Hui Guan 0001   +3 more
openaire   +2 more sources

Shapley Additive Explanation for Local Class Differentiation: Local Explainability for Class Differentiation in Classification Models

Advanced Intelligent Systems, EarlyView.
An instance‐level, model‐agnostic explanation of class differentiation is introduced through SHAP‐LCD, linking probability shifts to feature‐wise Shapley contributions. The method operates on tabular and image data and is released in a fully reproducible implementation, offering a transparent way to examine, at each instance, why predictive models ...
Roxana M. Romero Luna, Hugo A. Ordoñez Erazo, Carlos A. Cobos Lozada   +2 more
wiley   +1 more source

Progressive Training of Hybrid Clipped Rectified Linear Unit for Resilient Convolution Neural Networks

IEEE Access
Convolutional neural networks used in safety-critical systems must remain reliable under hardware-induced faults. Activation clipping is an effective fault-mitigation technique, yet existing approaches face a fundamental trade-off: layer-wise clipping ...
Seyedhamidreza Mousavi, Mohammad Hasan Ahmadilivani, Jaan Raik, Maksim Jenihhin, Masoud Daneshtalab   +4 more
doaj   +1 more source

Time‐Delayed Spiking Reservoir Computing Enables Efficient Time Series Prediction

Advanced Intelligent Systems, EarlyView.
This study proposes time‐delayed spiking reservoir computing (TDSRC) for efficient time series prediction. By concatenating time‐lagged states, TDSRC constructs an expanded readout feature vector without altering internal reservoir dynamics. This approach enables highly accurate forecasting with significantly fewer neurons, providing a resource ...
Pin Jin, Ren Cao, Zhongxue Gan, Siyang Leng   +3 more
wiley   +1 more source

Analysis and Prediction of Vertical Office Network Bandwidth Using a Backpropagation-Based Neural Network

Ilkom Jurnal Ilmiah
The digitalization of business and operational processes in vertical offices has transformed work behaviour, creating a critical need for stable internet connectivity to ensure smooth operations.
Muhammad Jamil Asshiddiq, Iffatul Mardhiyah   +1 more
doaj   +1 more source

Sex Prediction From the Clavicle Using Computerized Tomography Images via Traditional and Hybrid Deep Learning Models

Clinical Anatomy, EarlyView.
ABSTRACT The aim of this study is to perform high accuracy sex prediction from clavicle images using proposed hybrid deep learning models and traditional deep learning models. The clavicle of 807 female and 805 male individuals obtained from Computed Tomography were segmented in 3D format and saved in jpeg format as superior–inferior and right–left ...
Yusuf Secgin, Muhammet Cakmak, Deniz Senol, Seren Kaya, Oğuzhan Oztürk, Oğuzhan Harmandaoğlu, Hatice Yenigül, Eslem Yaren Bıyık, Omer Onbaş   +8 more
wiley   +1 more source

Implementation of Machine Learning Models to Predict Functionality of Pea Flour From Its Composition

Cereal Chemistry, EarlyView.
ABSTRACT Background and Objectives The goal of this research was to examine the relationship between the composition and functionality of pea flour using the following machine learning algorithms: linear regression, partial least squares regression (PLSR), Gaussian process regression (GPR), support vector regression, gradient‐boosted decision trees ...
Colten N. Nickerson, Sarah Hogarth, Andrea K. Stone, Gene C. Arganosa, Pankaj Bhowmik, Tom D. Warkentin, Jordan Ubbens, Michael T. Nickerson   +7 more
wiley   +1 more source

Machine Learning Paradigm for Advanced Battery Electrolyte Development

Carbon Energy, EarlyView.
Electrolyte materials determine ion transport kinetics within the bulk and interphases, ultimately influencing the performance of battery systems. As data‐driven paradigms increasingly reshape materials discovery, this review provides an application‐oriented exploration of the intersection between machine learning and electrolyte science. By evaluating
Chang Su, Mengfan Pei, Keyu Chen, Xigao Jian, Fangyuan Hu   +4 more
wiley   +1 more source