AIMC Topic: Neural Networks, Computer

Clear Filters Showing 3221 to 3230 of 31376 articles

ds-FCRN: three-dimensional dual-stream fully convolutional residual networks and transformer-based global-local feature learning for brain age prediction.

Brain structure & function
The brain undergoes atrophy and cognitive decline with advancing age. The utilization of brain age prediction represents a pioneering methodology in the examination of brain aging. This study aims to develop a deep learning model with high predictive...

Optimizing papermaking wastewater treatment by predicting effluent quality with node-level capsule graph neural networks.

Environmental monitoring and assessment
Papermaking wastewater consists of a sizable amount of industrial wastewater; hence, real-time access to precise and trustworthy effluent indices is crucial. Because wastewater treatment processes are complicated, nonlinear, and time-varying, it is e...

Incremental accumulation of linguistic context in artificial and biological neural networks.

Nature communications
Large Language Models (LLMs) have shown success in predicting neural signals associated with narrative processing, but their approach to integrating context over large timescales differs fundamentally from that of the human brain. In this study, we s...

A new pipeline with ultimate search efficiency for neural architecture search.

Neural networks : the official journal of the International Neural Network Society
We present a novel neural architecture search pipeline designed to enhance search efficiency through optimized data and algorithms. Leveraging dataset distillation techniques, our pipeline condenses large-scale target datasets into more streamlined p...

On latent dynamics learning in nonlinear reduced order modeling.

Neural networks : the official journal of the International Neural Network Society
In this work, we present the novel mathematical framework of latent dynamics models (LDMs) for reduced order modeling of parameterized nonlinear time-dependent PDEs. Our framework casts this latter task as a nonlinear dimensionality reduction problem...

Reducing bias in source-free unsupervised domain adaptation for regression.

Neural networks : the official journal of the International Neural Network Society
Due to data privacy and storage concerns, Source-Free Unsupervised Domain Adaptation (SFUDA) focuses on improving an unlabelled target domain by leveraging a pre-trained source model without access to source data. While existing studies attempt to tr...

CPJN: News recommendation with a content and popularity joint network.

Neural networks : the official journal of the International Neural Network Society
Users may click on a news because they are interested in its content or because the news contains important information and is very popular. Modeling these two aspects is crucial for accurate news recommendation. Most existing studies focused on capt...

DGMSCL: A dynamic graph mixed supervised contrastive learning approach for class imbalanced multivariate time series classification.

Neural networks : the official journal of the International Neural Network Society
In the Imbalanced Multivariate Time Series Classification (ImMTSC) task, minority-class instances typically correspond to critical events, such as system faults in power grids or abnormal health occurrences in medical monitoring. Despite being rare a...

When low-light meets flares: Towards Synchronous Flare Removal and Brightness Enhancement.

Neural networks : the official journal of the International Neural Network Society
Low-light image enhancement (LLIE) aims to improve the visibility and illumination of low-light images. However, real-world low-light images are usually accompanied with flares caused by light sources, which make it difficult to discern the content o...

Contrastive independent subspace analysis network for multi-view spatial information extraction.

Neural networks : the official journal of the International Neural Network Society
Multi-view classification integrates features from different views to optimize classification performance. Most of the existing works typically utilize semantic information to achieve view fusion but neglect the spatial information of data itself, wh...