AIMC Topic: Neural Networks, Computer

Clear Filters Showing 6881 to 6890 of 31376 articles

Distributed adaptive robust containment control for reaction-diffusion neural networks with external disturbances under directed graphs.

Neural networks : the official journal of the International Neural Network Society
In this paper, the leader-follower robust synchronization issue is mainly addressed for reaction-diffusion neural networks (RDNNs) with multiple leaders and external disturbances under directed graphs. Based on the σ modification approach, we propose...

A deep reinforcement learning algorithm framework for solving multi-objective traveling salesman problem based on feature transformation.

Neural networks : the official journal of the International Neural Network Society
As a special type of multi-objective combinatorial optimization problems (MOCOPs), the multi-objective traveling salesman problem (MOTSP) plays an important role in practical fields such as transportation and robot control. However, due to the comple...

Improved weight initialization for deep and narrow feedforward neural network.

Neural networks : the official journal of the International Neural Network Society
Appropriate weight initialization settings, along with the ReLU activation function, have become cornerstones of modern deep learning, enabling the training and deployment of highly effective and efficient neural network models across diverse areas o...

SLTRN: Sample-level transformer-based relation network for few-shot classification.

Neural networks : the official journal of the International Neural Network Society
Few-shot classification recognizes novel categories with limited labeled samples. The classic Relation Network (RN) compares support-query sample pairs for few-shot classification but overlooks support set contextual information, limiting its compari...

G2ViT: Graph Neural Network-Guided Vision Transformer Enhanced Network for retinal vessel and coronary angiograph segmentation.

Neural networks : the official journal of the International Neural Network Society
Blood vessel segmentation is a crucial stage in extracting morphological characteristics of vessels for the clinical diagnosis of fundus and coronary artery disease. However, traditional convolutional neural networks (CNNs) are confined to learning l...

Interactive attack-defense for generalized person re-identification.

Neural networks : the official journal of the International Neural Network Society
Generalized Person Re-Identification (GReID) aims to develop a model capable of robust generalization across unseen target domains, even with training on a limited set of observed domains. Recently, methods based on the Attack-Defense mechanism are e...

Composite attention mechanism network for deep contrastive multi-view clustering.

Neural networks : the official journal of the International Neural Network Society
Contrastive learning-based deep multi-view clustering methods have become a mainstream solution for unlabeled multi-view data. These methods usually utilize a basic structure that combines autoencoder, contrastive learning, or/and MLP projectors to g...

Optimizing removal of antiretroviral drugs from tertiary wastewater using chlorination and AI-based prediction with response surface methodology.

The Science of the total environment
Chemical and pharmaceutical chemicals found in water sources create substantial risks to human health and the environment. The presence of pharmaceutical contaminants in water can cause antibiotic resistance development, toxicity to aquatic organisms...

mRNA-CLA: An interpretable deep learning approach for predicting mRNA subcellular localization.

Methods (San Diego, Calif.)
Messenger RNA (mRNA) is vital for post-transcriptional gene regulation, acting as the direct template for protein synthesis. However, the methods available for predicting mRNA subcellular localization need to be improved and enhanced. Notably, few ex...

Enhanced thyroid nodule segmentation through U-Net and VGG16 fusion with feature engineering: A comprehensive study.

Computer methods and programs in biomedicine
BACKGROUND AND OBJECTIVE: The thyroid gland, a key component of the endocrine system, is pivotal in regulating bodily functions. Thermography, a non-invasive imaging technique utilizing infrared cameras, has emerged as a diagnostic tool for thyroid-r...