Assisting Training of Deep Spiking Neural Networks With Parameter Initialization [0.03%]
基于参数初始化的深度脉冲神经网络训练方法研究
Jianhao Ding,Jiyuan Zhang,Tiejun Huang et al.
Jianhao Ding et al.
Spiking neural networks (SNNs) exhibit significant advantages in terms of information encoding, computational capabilities, and power usage. We regard initializing weight distribution as a key problem for effective SNN training. When backpr...
Data-Based Model-Free Predictive Control System Under the Design Philosophy of MPC and Zeroing Neurodynamics for Robotic Arm Pose Tracking [0.03%]
基于MPC和零ing神经动力学的模型-free数据预测控制机器人姿态跟踪控制系统
Mengrui Cao,Lin Xiao,Qiuyue Zuo et al.
Mengrui Cao et al.
Involving both position and orientation tracking, pose tracking control for the end-effector of a redundant manipulator is a critical problem in robotic motion control. However, existing methods often suffer from dependency on model paramet...
Reinforcement Learning-Based Fault-Tolerant Control of Uncertain Strict-Feedback Nonlinear Systems With Intermittent Actuator Faults [0.03%]
基于强化学习的不确定严格反馈非线性系统间歇执行器故障容错控制
Qinmin Yang,Huaying Li,Zhengwei Ruan et al.
Qinmin Yang et al.
In this work, a novel reinforcement learning-based adaptive fault-tolerant control (FTC) scheme with actuator redundancy is presented for a nonlinear strict-feedback system with nonlinear dynamics and uncertainties. A learning-based switchi...
A Survey on Self-Supervised Monocular Depth Estimation Based on Deep Neural Networks [0.03%]
基于深度神经网络的自监督单目深度估计研究综述
Qiulei Dong,Zhengming Zhou,Xiaolan Qiu et al.
Qiulei Dong et al.
Monocular depth estimation aims to predict the corresponding scene depth map to an input image, which has wide application prospects in various fields, such as robot navigation, autonomous driving, and augmented reality. Due to the advantag...
Self-Organizing Stacked Type-2 Fuzzy Neural Network With Rule Generalization [0.03%]
具有规则概括的自组织堆叠型2模糊神经网络
Honggui Han,Chenxuan Sun,Xiaolong Wu et al.
Honggui Han et al.
Type-2 fuzzy neural networks (T2FNNs) are particularly effective in dealing with nonlinear systems. However, they inevitably suffer from multicollinearity problems caused by the significant overlaps of the footprint uncertainty (FOU), which...
Pseudo-Supervision Affinity Propagation for Efficient and Scalable Multiview Clustering [0.03%]
用于高效和可扩展的多视图聚类的伪监督亲和传播
Xinxin Wang,Yongshan Zhang,Yicong Zhou
Xinxin Wang
Anchor graph-based multiview clustering (AGMVC) demonstrates high efficiency and satisfactory performance. However, it still suffers from limitations such as single-structure similarity measurement, high time expenditure for large-scale anc...
Responding to News Sensitively in Stock Attention Networks via Prompt-Adaptive Trimodal Model [0.03%]
通过Prompt-自适应三模态模型在股票注意力网络中对新闻的敏感反应
Haotian Liu,Bowen Hu,Yadong Zhou et al.
Haotian Liu et al.
Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevi...
Diversify and Conquer: Open-Set Disagreement for Robust Semi-Supervised Learning With Outliers [0.03%]
多元化征服：带有异常值的鲁棒半监督学习的开放集不一致性的应用
Heejo Kong,Sung-Jin Kim,Gunho Jung et al.
Heejo Kong et al.
Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution; however, in practice, this assumption is easily violated, as unlabeled data often includes unknown class data...
Yueyi Zhang,Jin Wang,Wenming Weng et al.
Yueyi Zhang et al.
Recent research has explored leveraging event cameras, known for their prowess in capturing scenes with nonuniform motion, for video deraining, leading to performance improvements. However, the existing event-based method still faces the ch...
Sajad Darabi,Piotr Bigaj,Dawid Majchrowski et al.
Sajad Darabi et al.
Recently, there has been increasing interest in developing and deploying deep graph learning algorithms for various tasks, such as fraud detection and recommender systems. However, there is a limited number of publicly available graph-struc...