检索结果-南通市图书馆

在线全文

学校读者我要写书评

暂无评论

项目优化调度的多智能体社会进化算法

计算机研究与发展 2008年第6期45卷 998-1003页

作者：潘晓英焦李成西安电子科技大学智能信息处理研究所西安710071 西安电子科技大学智能感知与图像理解教育部重点实验室西安710071

结合多智能体系统、进化算法以及关系网模型,提出了一种多智能体社会进化算法用于求解项目活动的一个最优调度顺序以使整个工程的工期最短.每个智能体生存于环境中,为了增加自身能量将与其邻域展开竞争及协同操作,同时可利用自身的知识... 详细信息

结合多智能体系统、进化算法以及关系网模型,提出了一种多智能体社会进化算法用于求解项目活动的一个最优调度顺序以使整个工程的工期最短.每个智能体生存于环境中,为了增加自身能量将与其邻域展开竞争及协同操作,同时可利用自身的知识进行自学习来增加能量.根据项目优化调度的问题特点,设计了智能体的竞争行为、协同行为以及自学习行为.通过对PSPLIB中的标准问题进行测试,同时与其他启发式算法相比较的仿真实验结果表明该算法具有良好的性能,能在较短的时间内寻找到十分接近"最优解"的调度序列.

关键词：资源受限项目调度多智能体系统关系网模型竞争行为协作行为自学习行为

在线全文

学校读者我要写书评

暂无评论

类脑感知与认知的挑战与思考

智能系统学报 2022年第1期17卷 213-216页

作者：焦李成西安电子科技大学计算机科学与技术学部陕西西安710126

从脑科学和认知科学到人工智能,我们能够从生物物理机理中得到什么启发?推动认知人工智能,不仅需要“感知”也需要“认知”。本文首先对人工智能与深度学习的发展脉络进行了梳理与反思,在此基础上浅谈认知建模、自动学习和渐近演化。

关键词：深度学习人工智能自动学习脑科学物理机理认知建模认知科学挑战与思考

在线全文

学校读者我要写书评

暂无评论

全集成模拟神经网络理论与实现

西安交通大学学报 1989年第S1期23卷 127-131页

作者：焦李成西安交通大学电气工程系

基于 MOS VLSL 技术的最新进展,以 HopfieId 神经网络为对象,本文提出了全集成MOSFET-C 神经元和全集成 SC 神经元,给出了 MOSFET-C 神经网络和开关电容神经网络实现.从而为神经网络信息处理系统的分析、研制以及应用提供了新方法.1 MOS... 详细信息

基于 MOS VLSL 技术的最新进展,以 HopfieId 神经网络为对象,本文提出了全集成MOSFET-C 神经元和全集成 SC 神经元,给出了 MOSFET-C 神经网络和开关电容神经网络实现.从而为神经网络信息处理系统的分析、研制以及应用提供了新方法.1 MOSFET—C神经网络在模拟 VLSI 中,采用 MOS 工艺实现高质量的电容和运算放大器完全不成问题,如果进一步把 MOSFET 运用于非饱和区,构成所谓的压控电阻,就可获得所需的精确电阻,从而实现连续时间模拟处理器及系统的全集成化,称之为 MOSFET—C技术,然而,用 MOSFET

关键词：神经网络理论神经网络实现开关电容信息处理系统运算放大器压控非饱和区网络模型跨导联想记忆

A novel quantum-inspired immune clonal algorithm with the evolutionary game approach

在线全文

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2009年第10期19卷 1341-1347页

作者： Qiuyi Wu,licheng jiao,Yangyang Li,Xiaozheng Deng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China,Institute of Intelligent Information Processing,Xidian University,Xi’an 710071,China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China

The quantum-inspired immune clonal algorithm(QICA) is a rising intelligence *** on evolutionary game theory and QICA,a quantum-inspired immune algorithm embedded with evolutionary game(EGQICA) is proposed to solve combination optimization *** this paper,we map the quantum antibody’s finding the optimal solution to player’s pursuing maximum utility by choosing strategies in evolutionary *** dynamics is used to model the behavior of the quantum antibody and the memory mechanism is also introduced in this *** results indicate that the proposed approach maintains a good diversity and achieves superior performance.

关键词： Game theory Evolutionary game Replicator dynamics Quantum-inspired optimization Artificial immune system

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

基于加权投票集成的极化SAR图像分类方法

华中科技大学学报（自然科学版） 2015年第3期43卷 79-82页

作者：陈博王爽焦李成西安电子科技大学智能感知与图像理解教育部重点实验室陕西西安710071 西安电子科技大学智能感知与计算国际联合研究中心陕西西安710071

提出了一种新的基于加权投票准则集成的极化合成孔径雷达系统(PolSAR)图像分类方法.该方法采用加权投票集成的方法根据不同个体的学习结果进行合,并从而提高极化SAR图像的分类精度.首先,输入极化图像数据并获得所需要的特征作为特征集.... 详细信息

提出了一种新的基于加权投票准则集成的极化合成孔径雷达系统(PolSAR)图像分类方法.该方法采用加权投票集成的方法根据不同个体的学习结果进行合,并从而提高极化SAR图像的分类精度.首先,输入极化图像数据并获得所需要的特征作为特征集.再从图像的每一类中选取多组像素点组成多个训练样本子集;然后,基于不同的样本子集训练学习得到不同的分类器,并对像素点进行分类得到预测标记,再由这些预测标记计算得出相应的加权系数;最后,通过加权系数将预测标记合并起来得到最终的极化SAR分类结果.实验结果证明,所提出的算法在AIRSAR和Radarsat-2数据上取得了很好的分类结果.

关键词：图像分类雷达极化监督分类极化SAR图像分类分类器集成加权投票准则

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

在线全文

学校读者我要写书评

暂无评论

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 Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 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

Intelligent multi-user detection using an artificial immune system

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science in China(Series F) 2009年第12期52卷 2342-2353页

作者： GONG MaoGuo, jiao licheng, MA WenPing & MA JingJing Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing, Xidian University, Xi’an 710071, China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi’an China Institute of Intelligent Information Processing Xidian University Xi’an China

Artificial immune systems （AIS） are a kind of new computational intelligence methods which draw inspiration from the human immune system. In this study, we introduce an AIS-based optimization algorithm, called clonal selection algorithm, to solve the multi-user detection problem in code-division multipleaccess communications system based on the maximum-likelihood decision rule. Through proportional cloning, hypermutation, clonal selection and clonal death, the new method performs a greedy search which reproduces individuals and selects their improved maturated progenies after the affinity maturation process. Theoretical analysis indicates that the clonal selection algorithm is suitable for solving the multi-user detection problem. Computer simulations show that the proposed approach outperforms some other approaches including two genetic algorithm-based detectors and the matched filters detector, and has the ability to find the most likely combinations.

关键词： artificial immune systems clonal selection multi-user detection code-division multiple-access genetic algorithm

A Wavelet-Based Fuzzy Neural Network for Interpolation of Fuzzy If-Then Rules

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 1998年第4期9卷 65-74页

作者： jiao licheng Liu Fang Wang Ling & Zhang Yanning(State Key Lab. of RSP and Center for Neural Networks, Xidian University, Xi’an 710071, P. R. China) (This project was partly supported by the National Thud of Intercent. Expert and partly supported bythe State Key Lab. of RSP and Center for Neural Networks Xidian University Xian 710071 P. R. China

In this paper, a wavelet-based fuzzy neural network with its structure and a learningalgorithm is proposed and the simulation results are given to prove its feasibility.

关键词： Fuzzy reasoning WBFRNN Learning algorithm

APPROXIMATION MULTIDIMENSION FUCTION WITH FUNCTIONAL NETWORK

在线全文

学校读者我要写书评

暂无评论

Journal of Electronics(China) 2006年第1期23卷 81-84页

作者： Li Weibin Liu Fang jiao licheng Zhang Shuling Li Zongling Institute of Graphics and Image Processing Xianyang Normal University Xianyang 712000 China National Key Laboratory for Radar Signal Processing Xidian University Xi＇an 710071 China Insititute of Intelligent Information Processing Xidian University Xi＇an 710071 China

The functional network was introduced by ***, which extended the neural network. Not only can it solve the problems solved, but also it can formulate the ones that cannot be solved by traditional network. This paper applies functional network to approximate the multidimension function under the ridgelet theory. The method performs more stable and faster than the traditional neural network. The numerical examples demonstrate the performance.

关键词： Functional network Ridgelet Approximation