Deep Residual Echo State Networks: Exploring Residual Orthogonal Connections in Untrained Recurrent Neural Networks [0.03%]
深度残差回声状态网络：在未经训练的循环神经网络中探索残差正交连接
Matteo Pinna,Andrea Ceni,Claudio Gallicchio
Matteo Pinna
Echo state networks (ESNs) are a particular type of untrained recurrent neural networks (RNNs) within the reservoir computing (RC) framework, popular for their fast and efficient learning. However, traditional ESNs often struggle with long-...
DHMNN: A Hypergraph Motif-Based Framework for Directed Hyperlink Prediction [0.03%]
基于超图动机的有向 hyperlink预测框架 DHMNN
Xihang Meng,Hao Peng,Guangjie Zeng et al.
Xihang Meng et al.
Directed hypergraphs have gained increasing attention for modeling group interactions while preserving directionality. However, link prediction in directed hypergraphs has rarely been studied despite its practical significance in complex sy...
Xiujuan Sun,Fuzhen Sun,Wenxuan Zhang et al.
Xiujuan Sun et al.
Recent advances in deep learning have greatly facilitated the improvement of Transformer-based sequential recommendation (SR) algorithms. However, the current methods still suffer from the following problems: 1) insufficient generalization ...
Andreas Papachristodoulou,Christos Kyrkou,Stelios Timotheou et al.
Andreas Papachristodoulou et al.
Local layer-wise learning offers modular optimization, layer-level transparency, and training without end-to-end error transport. However, its scalability remains limited by three coupled difficulties: local objectives can be weak or poorly...
Stable and Accurate Robot Trajectory Tracking Using Variable-Stiffness Euclideanizing Flow [0.03%]
基于变刚度欧氏流的稳定准确机器人轨迹跟踪方法
Tianming Zhang,Yanmin Zhou,Pengpeng Zhang et al.
Tianming Zhang et al.
Imitation learning based on dynamical systems (DSs) can generate real-time motion planning with intrinsic stability and robustness, providing significant advantages in highly uncertain dynamic environments. However, most DS approaches tend ...
Jongmin Yu,Zhongtian Sun,Konstantinos Panagiotis Alexandridis et al.
Jongmin Yu et al.
This article presents a novel approach to video frame interpolation (VFI), called latent diffusion for stable frame interpolation (LD4SFI). LD4SFI leverages a latent diffusion model (LDM) enhanced by a vector-quantized spatiotemporal variat...
Spike-EIFNet: Lightweight Spike-Driven Event-Image Fusion Network for Accurate and Efficient Semantic Segmentation [0.03%]
基于轻量级脉冲驱动事件图像融合网络的精确高效语义分割模型
Siyu Chen,Qie Liu,Xianlei Long et al.
Siyu Chen et al.
Semantic segmentation is critical for intelligent robotics to understand complex environments. While CNN-based models on RGB images achieve high performance, their accuracy drops in fast-motion or low-light scenes. Fortunately, event camera...
Measuring Model-Induced Discrimination via Efficient Fairness Approximation [0.03%]
通过有效公平近似测量模型引起的歧视
Yijun Bian,Yujie Luo
Yijun Bian
Providing various machine learning (ML) applications in the real world, concerns about discrimination hidden in ML models are growing, particularly in high-stakes domains. Existing techniques for assessing the discrimination level of ML mod...
TrafficFlowNet: A Neural Transport Model for Dynamic Traffic Flows [0.03%]
TrafficFlowNet：一种动态交通流神经传输模型
Xinwei Huang,Tianmu Hu,Ruxiang Duan et al.
Xinwei Huang et al.
Traffic congestion remains a persistent barrier to mobility and efficiency, especially in developing regions with limited infrastructure. Addressing this challenge requires robust traffic flow modeling, which remains challenging due to nonl...
An Ensemble Learning Approach to Graph Learning Based on Evolutionary Graph Neural Architecture Search [0.03%]
基于进化图神经架构搜索的图学习集成学习方法
Wei-Feng Guo,Pengyu Wang,Ying Bi et al.
Wei-Feng Guo et al.
The graph neural networks (GNNs) have been successfully applied to non-Euclidean graph data mining tasks, attracting widespread attention. At present, to achieve promising performance, many researchers use neural architecture search (NAS) o...