AI Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 351 to 360 of 2841 articles

Clear Filters

Generalized zero-shot learning via discriminative and transferable disentangled representations.

Neural networks : the official journal of the International Neural Network Society
In generalized zero-shot learning (GZSL), it is required to identify seen and unseen samples under the condition that only seen classes can be obtained during training. Recent methods utilize disentanglement to make the information contained in visua...

Delayed-feedback oscillators replicate the dynamics of multiplex networks: Wavefront propagation and stochastic resonance.

Neural networks : the official journal of the International Neural Network Society
The widespread development and use of neural networks have significantly enriched a wide range of computer algorithms and promise higher speed at lower cost. However, the imitation of neural networks by means of modern computing substrates is highly ...

Hybrid contrastive multi-scenario learning for multi-task sequential-dependence recommendation.

Neural networks : the official journal of the International Neural Network Society
Multi-scenario and multi-task learning are crucial in industrial recommendation systems to deliver high-quality recommendations across diverse scenarios with minimal computational overhead. However, conventional models often fail to effectively lever...

Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis.

Neural networks : the official journal of the International Neural Network Society
Functional connectivity (FC), derived from resting-state functional magnetic resonance imaging (rs-fMRI), has been widely used to characterize brain abnormalities in disorders. FC is usually defined as a correlation matrix that is a symmetric positiv...

Illumination-Guided progressive unsupervised domain adaptation for low-light instance segmentation.

Neural networks : the official journal of the International Neural Network Society
Due to limited photons, low-light environments pose significant challenges for computer vision tasks. Unsupervised domain adaptation offers a potential solution, but struggles with domain misalignment caused by inadequate utilization of features at d...

CDCGAN: Class Distribution-aware Conditional GAN-based minority augmentation for imbalanced node classification.

Neural networks : the official journal of the International Neural Network Society
Node classification is a fundamental task of Graph Neural Networks (GNNs). However, GNN models tend to suffer from the class imbalance problem which deteriorates the representation ability of minority classes, thus leading to unappealing classificati...

Large Language Model Enhanced Logic Tensor Network for Stance Detection.

Neural networks : the official journal of the International Neural Network Society
Social media platforms, rich in user-generated content, offer a unique perspective on public opinion, making stance detection an essential task in opinion mining. However, traditional deep neural networks for stance detection often suffer from limita...

Generalization analysis of adversarial pairwise learning.

Neural networks : the official journal of the International Neural Network Society
Adversarial pairwise learning has become the predominant method to enhance the discrimination ability of models against adversarial attacks, achieving tremendous success in various application fields. Despite excellent empirical performance, adversar...

Beyond homophily in spatial-temporal traffic flow forecasting.

Neural networks : the official journal of the International Neural Network Society
Traffic flow forecasting is a crucial yet complex task due to the intricate spatial-temporal correlations arising from road interactions. Recent methods model these interactions using message-passing Graph Convolution Networks (GCNs), which work for ...

Tensor ring rank determination using odd-dimensional unfolding.

Neural networks : the official journal of the International Neural Network Society
While tensor ring (TR) decomposition methods have been extensively studied, the determination of TR-ranks remains a challenging problem, with existing methods being typically sensitive to the determination of the starting rank (i.e., the first rank t...