Large language models (LLMs) play a crucial role in various Natural Language Processing (NLP) tasks, prompting their deployment on mobile devices for inference. However, a significant challenge arises due to high waiting latency, especially for long ...

Multi-metric learning is important for improving performance of learners. For complex data, multi metric learning algorithms need intensive research. Moreover, the existing multi-metric learning methods may lead to the distance not being ...

Distance metric learning has been a promising technology to improve the performance of algorithms related to distance metrics. The existing distance metric learning methods are either based on the class center or the nearest neighbor ...

Metric learning has attracted significant attention due to its high effectiveness and efficiency for pattern recognition task. Traditional supervised metric learning algorithms attempt to seek a global distance metric with labeled samples. When ...

This paper exploits the potential of a high-order implicit radial basis function-based differential quadrature-finite volume (IRBFDQ-FV) method for effective simulation of inviscid and viscous compressible flows using unstructured grids. The ...

• Compressible inviscid and viscous flow problems are solved by the present high-order method on unstructured grids.
• RBFDQ meshless method is locally employed for derivative approximation.
• Convective and viscous fluxes at the cell ...

The coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically ...

• MIP can identify changes in vascular morphology and COVID-19 lesions in CT images.

Multi-metric learning is important for improving classification performance since learning a single metric is usually insufficient for complex data. The existing multi-metric learning methods are based on the triplet constraints, and thus are with ...

Multi-metric learning plays a significant role in improving the generalization of algorithms related to distance metrics since using a single metric is sometimes insufficient to handle complex data. Metric learning can adjust ...

Distance metric learning plays a significant role in improving the generalization of algorithms related to distance metrics. In this paper, we first propose a generalized Mahalanobis metric learning framework (called GLML) to make use ...

This paper combines the multilayer perceptron (MLP) and the radial basis function (RBF) neural networks to design a hybrid multilayer perceptron-radial basis function (HMLP-RBF) neural network for solving the hyperbolic conservation laws without ...

Correntropy is a locally second-order statistical measure in kernel space. The different kernel functions induce different correntropy with different properties. In this work, we propose an asymmetric mixture kernel and the corresponding ...

Metric learning has been a promising technology to improve classification performance, which aims to learn a data-dependent distance metric such that the similarity between samples can be more effectively evaluated. Metric plays a ...

Metric learning has attracted a lot of interest in classification tasks due to its efficient performance. Most traditional metric learning methods are based on k-nearest neighbors (kNN) classifiers to make decisions, while the choice k ...

Extreme learning machine (ELM) has attracted widespread attention due to its simple, quick and good performance. In this work, in order to deal with cross data quickly and efficiently, we first propose generalized eigenvalue proximal extreme ...

• The macroscopic equations with actual numerical dissipative terms of the LBFS are derived.

The lattice Boltzmann flux solver (LBFS) uses the finite volume method (FVM) to update macroscopic variables while uses the local solution of lattice Boltzmann equation (LBE) to calculate fluxes at the cell interface. It overcomes the ...

• Perform simultaneously subspace learning and metric learning (psub).
• Enhance ...

Distance metric learning has been an important technique in machine learning field recently due to its high effectiveness in improving the performance of distance related methods. In order to take advantages of both subspace learning ...

Chest computed tomography (CT) is crucial in the diagnosis of coronavirus disease 2019 (COVID-19). However, the persistent pandemic and similar CT manifestations between COVID-19 and community-acquired pneumonia (...

• The fully automatic pipeline of deep learning can distinguish COVID-19 from CAP.

• The implicit LBFS is proposed aiming to efficiently simulate both steady and unsteady flows.

The lattice Boltzmann flux solver (LBFS) is a novel Boltzmann-typed solver under the finite volume framework, which has many advantages over traditional lattice Boltzmann equation (LBE) solvers. However, the existing versions of LBFS ...

Semi-supervised learning is an attractive technique for using unlabeled data in classification. In this work, an efficient semi-supervised extreme learning machine (ELM) classification framework is proposed by introducing the Laplacian ...

Multi-metric learning is an important technique for improving classification performance since learning a single metric is usually insufficient for complex data. Most of the existing multi-metric learning approaches have high ...