2-D Transformer: Extending Large Language Models to Long-Context With Few Memory [0.03%]
2-D Transformer：通过少量内存将大型语言模型扩展到长上下文环境中
Xingyang He,Jie Liu,Yutai Duan
Xingyang He
The ability of processing long contexts is crucial for large language models (LLMs), but training LLMs with a long-context window requires substantial computational resources. Many sought to mitigate this through the sparse attention mechan...
Efficient Linear Discriminant Analysis Based on Randomized Low-Rank Approaches [0.03%]
基于随机低秩方法的有效线性判别分析
Yujie Wang,Weiwei Xu,Lei Zhu
Yujie Wang
Linear discriminant analysis (LDA) faces challenges in practical applications due to the small sample size (SSS) problem and high computational costs. Various solutions have been proposed to address the SSS problem in both ratio trace LDA a...
MSAFF: Multi-Way Soft Attention Fusion Framework With the Large Foundation Models for the Diagnosis of Alzheimer's Disease [0.03%]
MSAFF：基于大型基础模型的多路软注意力融合框架在阿尔茨海默病诊断中的应用
Xia-An Bi,Wenzhuo Shen,Yinglu Shan et al.
Xia-An Bi et al.
Complementary information in multi-omics data are crucial for understanding the pathogenesis of Alzheimer's Disease (AD). However, existing studies face challenges in addressing the high-level noise and heterogeneity in multi-omics data. Th...
Deep CNN Feature Resampling and Ensemble Based on Cross Validation for Image Classification [0.03%]
基于交叉验证的深度卷积特征重采样与集成分类研究
Yu Wang,Haodong Zhang,Xingli Yang et al.
Yu Wang et al.
Deep convolutional neural networks (CNNs) such as AlexNet, VGGNet, ResNet, EfficientNet, and MobileNet have been extensively employed in image classification tasks. A common solution is directly feeding deep CNN features extracted from a de...
BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction [0.03%]
基于行为伪标签的稀疏图卷积网络行人及异构轨迹预测方法研究
Ruochen Li,Stamos Katsigiannis,Tae-Kyun Kim et al.
Ruochen Li et al.
Trajectory prediction allows better decision-making in applications of autonomous vehicles (AVs) or surveillance by predicting the short-term future movement of traffic agents. It is classified into pedestrian or heterogeneous trajectory pr...
A Robust Multi-Virtual-Agent Inverse Reinforcement Learning Approach With Data Aggregation for Perturbed Environments [0.03%]
用于扰动环境的具有数据聚合同的鲁棒多虚拟智能体逆强化学习方法
Yanbin Lin,Zhen Ni
Yanbin Lin
Learning control in environments with uncertainties and perturbations remains a challenging issue in the field of artificial intelligence. Though conventional imitation learning (IL) and inverse reinforcement learning (IRL) methods have mad...
Unifying Attribute and Structure Preservation for Enhanced Graph Contrastive Learning [0.03%]
增强图对比学习的属性和结构保存统一方面方法
Jialu Chen,Rui Chen,Gang Kou
Jialu Chen
The graph contrastive learning (GCL) has garnered significant interest due to its strong capability to capture both graph structure and node attribute information through self-supervised learning. However, current GCL frameworks primarily c...
Unveiling the Tapestry: The Interplay of Generalization and Forgetting in Continual Learning [0.03%]
揭开织锦：持续学习中泛化与遗忘的相互作用
Zenglin Shi,Jie Jing,Ying Sun et al.
Zenglin Shi et al.
In artificial intelligence (AI), generalization refers to a model's ability to perform well on out-of-distribution data related to the given task, beyond the data it was trained on. For an AI agent to excel, it must also possess the continu...
Neural-Network-Based Recursive State Estimation for Nonlinear Networked Systems With Binary-Encoding Mechanisms [0.03%]
基于神经网络的二值编码非线性网络系统状态递归估计
Yuhan Zhang,Zidong Wang,Lei Zou et al.
Yuhan Zhang et al.
This work addresses the problem of recursive state estimation for networked control systems with unknown nonlinearities and binary-encoding mechanisms (BEMs). To enhance transmission reliability and reduce network resource consumption, BEMs...
SPCNet: Deep Self-Paced Curriculum Network Incorporated With Inductive Bias [0.03%]
SPCNet：结合归纳偏置的深度自我加速课程网络
Yue Zhao,Maoguo Gong,Mingyang Zhang et al.
Yue Zhao et al.
The vulnerability to poor local optimum and the memorization of noise data limit the generalizability and reliability of massively parameterized convolutional neural networks (CNNs) on complex real-world data. Self-paced curriculum learning...