Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
A reinforcement learning (RL) method based on the multi-head self-attention (MSA) mechanism is proposed to solve the challenge of multiple unmanned surface vehicles (multi-USV) hunting target at the surface. The kinematic, dynamic, and environmental ...
Epilepsy research
Sep 1, 2025
In recent years, Artificial Intelligence (AI), with a specific emphasis on attention mechanisms instead of conventional Deep Learning (DL) or Machine Learning (ML), has demonstrated significant applicability across diverse medical domains. This paper...
Magnetic resonance imaging
Sep 1, 2025
UNLABELLED: Synthetic MRI (SyMRI) is a technique used to estimate tissue properties and generate multiple MR sequence contrasts from a single acquisition. However, image quality can be suboptimal.
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Synaptic increase is a common phenomenon in the brain of autism spectrum disorder (ASD). However, the impact of increased synapses on the neurophysiological activity of ASD remains unclear. To address this, we propose a large-scale cortical network m...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Neural networks often excel in short-horizon tasks, but their long-term reliability is less assured. We demonstrate that even a minimal architecture, trained on near-periodic data, can exhibit hyperbolic chaotic behavior after a small parameter pertu...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, there is often a significant performance drop compared to their full-pre...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
In the field of healthcare, the acquisition and annotation of medical images present significant challenges, resulting in a scarcity of trainable samples. This data limitation hinders the performance of deep learning models, creating bottlenecks in c...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Recent assessments of Multi-Modal Large Language Models (MLLMs) have been thorough. However, a detailed benchmark that integrates point cloud data with language for MLLMs remains absent, leading to superficial comparisons that obscure advancements in...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
DNA logic circuits are essential building blocks for molecular computers. Traditional molecular logic circuits primarily use basic gate circuits as computational units, achieving complex functions via multiple cascades. However, even simple logical f...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Effective molecular representation learning (MRL) is essential for advancing molecular property prediction. In recent years, graph-based MRL methods have made significant progress by effectively utilizing the topology structure of molecules. Research...