检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2022年第6期3卷 887-907页

作者： Jiao, Licheng Yang, Yuting Liu, Fang Yang, Shuyuan Hou, Biao Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China School of Artificial Intelligence Xi'an710071 China

In recent years, the enormous demand for computing resources resulting from massive data and complex network models has become the limitation of deep learning. In the large-scale problems with massive samples and ultrahigh feature dimensions, sparsity has gradually drawn much attention from academia and the industrial field. In this article, the new generation of brain-inspired sparse learning is reviewed comprehensively. First, sparse cognition learning is introduced from the visual biology mechanism to modeling for the natural image. Second, the sparse representation algorithms are summarized to sort out the research progress of sparse learning. Third, the relevant research on sparse feature selection learning is reviewed. Then, the sparse deep networks and applications are summed up. Last but not least, ten public issues and challenges of sparse learning are discussed. By investigating the development process of sparse learning, this article summarizes the advantages, disadvantages, limitations, and future research directions of the algorithm, which can help readers conduct further study. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CLUSTERING VIA DIMENSIONAL REDUCTION METHOD FOR THE PROJECTION PURSUIT BASED ON THE ICSA

引用

Journal of Electronics(China) 2010年第4期27卷 474-479页

作者： Gou Shuiping Feng Jing Jiao Licheng Key Laboratory of Intelligent Perception and Image Understanding for the Ministry of Education Institute of Intelligent Information Processing Xidian University Xi＇an 710071 China

The performance of the classical clustering algorithm is not always satisfied with the high-dimensional datasets, which make clustering method limited in many application. To solve this problem, clustering method with Projection Pursuit dimension reduction based on Immune Clonal Selection Algorithm (ICSA-PP) is proposed in this paper. Projection pursuit strategy can maintain consistent Euclidean distances between points in the low-dimensional embeddings where the ICSA is used to search optimizing projection direction. The proposed algorithm can converge quickly with less iteration to reduce dimension of some high-dimensional datasets, and in which space, K-mean clustering algorithm is used to partition the reduced data. The experiment results on UCI data show that the presented method can search quicker to optimize projection direction than Genetic Algorithm (GA) and it has better clustering results compared with traditional linear dimension reduction method for Principle Component Analysis (PCA).

关键词： Projection Pursuit (PP) Immune Clonal Selection Algorithm (ICSA) Genetic Algorithm (GA) K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Adaptive multifactorial particle swarm optimisation

引用

CAAI Transactions on Intelligence Technology 2019年第1期4卷 37-46页

作者： Zedong Tang Maoguo Gong School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding of Ministry of EducationXidian UniversityNo.2 South TaiBai RoadXi’an 710071People’s Republic of China

Existing multifactorial particle swarm optimisation(MFPSO)algorithms only explore a relatively narrow area between the inter-task ***,these algorithms use a fixed inter-task learning probability throughout the evolution ***,the parameter is problem dependent and can be various at different stages of the *** this work,the authors devise an inter-task learning-based information transferring mechanism to replace the corresponding part in *** inter-task learning mechanism transfers the searching step by using a differential term and updates the personal best position by employing an inter-task *** this mean,the particles can explore a broad search space when utilising the additional searching experiences of other *** addition,to enhance the performance on problems with different complementarity,they design a self-adaption strategy to adjust the inter-task learning probability according to the performance *** compared the proposed algorithm with the state-of-the-art algorithms on various benchmark *** results demonstrate that the proposed algorithm can transfer inter-task knowledge efficiently and perform well on the problems with different complementarity.

关键词： MFPSO multifactorial particle swarm optimisation

来源：评论

学校读者我要写书评

暂无评论

Memetic computation based on regulation between neural and immune systems: the framework and a case study

引用

Science China(Information Sciences) 2010年第8期53卷 1519-1527页

作者： GONG MaoGuo , JIAO LiCheng, LIU Fang & YANG Jie key Lab of intelligent perception and image understanding of ministry of education of China, Institute of intelligent Information Processing, Xidian University, Xi’an 710071, China 1. Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China

Lamarckian learning has been introduced into evolutionary computation to enhance the ability of local search. The relevant research topic, memetic computation, has received significant amount of interest. In this study, a novel memetic computational framework is proposed by simulating the integrated regulation between neural and immune systems. The Lamarckian learning strategy of simulating the unidirectional regulation of neural system on immune system is designed. Consequently, an immune memetic algorithm based on the Lamarckian learning is proposed for numerical optimization. The proposed algorithm combines the advantages of immune algorithms and mathematical programming, and performs well in both global and local search. The simulation results based on ten low-dimensional and ten high-dimensional benchmark problems show that the immune memetic algorithm outperforms the basic genetic algorithm-based memetic algorithm in solving most of the test problems.

关键词： memetic computation artificial immune system Lamarckian learning genetic algorithm numerical optimization

来源：评论

学校读者我要写书评

暂无评论

Graph Representation Learning Meets Computer Vision: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 2-22页

作者： Jiao, Licheng Chen, Jie Liu, Fang Yang, Shuyuan You, Chao Liu, Xu Li, Lingling Hou, Biao Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China International Research Center of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi'an710071 China

A graph structure is a powerful mathematical abstraction, which can not only represent information about individuals but also capture the interactions between individuals for reasoning. Geometric modeling and relational inference based on graph data is a long-standing topic of interest in the computer vision community. In this article, we provide a systematic review of graph representation learning and its applications in computer vision. First, we sort out the evolution of representation learning on graphs, categorizing them into the nonneural network and neural network methods based on the way the nodes are encoded. Specifically, nonneural network methods, such as graph embedding and probabilistic graphical models, are introduced, and neural network methods, such as graph recurrent neural networks, graph convolutional networks, and variants of graph neural networks, are also presented. Then, we organize the applications of graph representation algorithms in various vision tasks (such as image classification, semantic segmentation, object detection, and tracking) for review and reference, and the typical graph construction approaches in computer vision are also summarized. Finally, on the background of biology and brain inspiration, we discuss the existing challenges and future directions of graph representation learning and computer vision. © 2022 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Fast non-local Lee filter for SAR image despeckling using directional projection

Fast non-local Lee filter for SAR image despeckling using di...

引用

6th International Conference on Radar, RADAR 2011

作者： Hua, Zhong Lu, Lu Jiao, Lc Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an 710071 China

ISBN: (纸本)9781424484416

This paper combines the Lee filter with the non-local mean filter, and a new similarity measure is derived based on the statistics of speckle noise, which extended the non-local means from the additive noise to the multiplicative noise. Also directional projection is adopted to accelerate the process of similarity computation. The results show its effectiveness. Experimental results illustrate that the proposed method can effectively smooth the speckle while preserving the details with reduced complexity. © 2011 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Learning of sparse fuzzy cognitive maps using evolutionary algorithm with lasso initialization 11th

Learning of sparse fuzzy cognitive maps using evolutionary a...

引用

11th International Conference on Simulated Evolution and Learning, SEAL 2017

作者： Wu, Kai Liu, Jing Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi’an710071 China

ISBN: (纸本)9783319687582

Fuzzy cognitive maps (FCMs), characterized by a great deal of abstraction, flexibility, adaptability, and fuzzy reasoning, are widely used tools for modeling dynamic systems and decision support systems. Research on the problem of finding sparse FCMs from observed data is outstanding. Evolutionary algorithms (EAs) play a key role in learning FCMs from time series without expert knowledge. In this paper, we first involve sparsity penalty in the objective function optimized by EAs. To improve the performance of EAs, we develop an effective initialization operator based on the Lasso, a convex optimization approach. Comparative experiments on synthetic data with varying sizes and densities compared with other state-of-the-art methods demonstrate the effectiveness of the proposed approach. Moreover, the proposed initialization operator is able to promote to performance of EAs in learning sparse FCMs from time series. © Springer International Publishing AG 2017.

关键词： Fuzzy Cognitive Maps

来源：评论

学校读者我要写书评

暂无评论

Emergency logistics scheduling in disaster relief based on a multi-agent genetic algorithm

Emergency logistics scheduling in disaster relief based on a...

引用

2016 IEEE Congress on Evolutionary Computation, CEC 2016

作者： Gan, Xiaohui Liu, Jing Hao, Xingxing Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an710071 China

ISBN: (纸本)9781509006229

The disaster emergency relief plays a vital role in reducing casualties and economic losses. Emergency logistics scheduling (ELS) aims at dispatching emergency resources to the victims of disasters, which is an important event of disaster relief. In this paper, a model for ELS in disaster relief is built that includes several suppliers with a variety of resources, several kinds of vehicles, and multiple disasters. To ensure timely and effective dispatching, an objective is first designed to minimize the completion time of scheduling and the total unsatisfied time of the whole relief. Then, a multi-agent genetic algorithm (MAGA) is proposed to solve this problem. Four evolutionary operators, namely, the crossover, mutation, self-learning and the effective neighborhood competition operators are designed for agents. The proposed algorithm is applied to the case of Chi-Chi earthquake in Taiwan, and the experimental results show that the performance of this algorithm is better than that of genetic algorithm and memetic algorithm. © 2016 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary algorithm for enhancing the robustness of networks 11th

Multi-objective evolutionary algorithm for enhancing the rob...

引用

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Li, Zheng Wang, Shanfeng Ma, Wenping Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xian710071 China

ISBN: (纸本)9789811036132

Networks can represent many real-world complex systems. Systems like internet, power grids and fuel distribution networks need to be robust and capable of surviving from failures or intentional attacks. In recent years, the measurements node-robustness and link-robustness have attracted many researchers, and some researchers use different methods to enhance one of them or both of them. In this paper, we put forward a new method which is to use a multi-objective evolutionary algorithm to enhance both these two kinds of robustness of networks against attacks. We define two objective functions which represent noderobustness and link-robustness respectively. Experiments show that our algorithm can find a good balance between improving node-robustness and link-robustness. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A multi-objective immune algorithm for human motion tracking

A multi-objective immune algorithm for human motion tracking

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Han, Hong Feng, Guangjie Gou, Jingxiang Wang, Rui Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi'an China

ISBN: (纸本)9781612847740

A crucial challenge in human body tracking is the high degrees of freedom (up to around 40) to be recovered. A method based on multi-objective optimization algorithm is presented here to tackle this problem. In our multi-objective optimization based human body tracking framework, tracking is considered as two functions' co-optimization problem where the aim is to optimize the matching functions between the model projection and the image observation. Experiments on 3D human motion tracking demonstrate the effectiveness and computational efficiency of the proposed tracking method. © 2011 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：