检索结果-内蒙古大学图书馆

Improved self-organizing maps and speech compression

International Journal of computer Science Issues 2012年第2期9卷 197-205页

作者： Ettaouil, Mohamed Lazaar, Mohamed UFR: Scientific Computing and Computer sciences Engineering sciences Modeling and Scientific Computing Laboratory Faculty of Science and Technology of Fez University Sidi Mohammed ben Abdellah Box 2202 Fez Morocco

Recent developments of Self-Organizing Maps or Kohonen networks become more and more interesting in many fields such as: pattern recognition, clustering, speech recognition, data compression, medical diagnosis... Kohonen networks is unsupervised learning models. The results obtained by the Kohonen networks are dependent on their parameters such as the architecture of the Kohonen map, the later has a great impact on the convergence of learning methods. The selection of the architecture of Kohonen networks, associated with a given problem, is one of the most important research problems in the neural network research. In this paper, we model this problem of neural architecture in terms of a mixed-integer non linear problem with linear constraints. To solve this model of optimization for the network architectures, we propose the genetic algorithm. Also, we implemented and evaluated the proposed method and speech compression algorithms. Speech compression is the technology of converting human speech into an efficiently encoded representation that can later be decoded to produce a close approximation of the original signal. The numerical results demonstrated the effectiveness of the new model. © 2012 International Journal of computer Science Issues.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Neural architectures optimization and genetic algorithms

引用

WSEAS Transactions on computers 2009年第3期8卷 526-537页

作者： Ettaouil, Mohamed Ghanou, Youssef UFR: Scientific Calculation and Computing Engineering Sciences Department of Mathematics and Computer Science University Sidi Mohammed Ben Abdellah Fez Box 2202 Fez Morocco

The artificial neural networks (ANN) have proven their efficiency in several applications: pattern recognition, voice and classification problems. The training stage is very important in the ANN's performance. The selection of the architecture of a neural network suitable to solve a given problem is one of the most important aspects of neural network research. The choice of the hidden layers number and the values of weights has a large impact on the convergence of the training algorithm. In this paper we propose a mathematical formulation in order to determine the optimal number of hidden layers and good values of weights. To solve this problem, we use genetic algorithms. The numerical results assess the effectiveness of the theorical results shown in this paper and computational experiments are presented, and the advantages of the new modelling.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Maximal constraint satisfaction problems solved by continuous hopfield networks

引用

WSEAS Transactions on computers 2013年第2期12卷 29-40页

作者： Ettaouil, Mohamed Loqman, Chakir Haddouch, Khalid Hami, Youssef UFR: Scientific Computing and Computer sciences Engineering Sciences Modeling and Scientific Computing Laboratory Faculty of Science and Technology of Fez University Sidi Mohammed ben Abdellah Box 2202 Fez Morocco Department of Computer Engineering High School of Technology Moulay Ismaïl University B. P. 3103 50000 Toulal Meknes Morocco

In this paper, we propose a new approach to solve the maximal constraint satisfaction problems (Max-CSP) using the continuous Hopfield network. This approach is divided into two steps: the first step involves modeling the maximal constraint satisfaction problem as 0-1 quadratic programming subject to linear constraints (QP). The second step concerns applying the continuous Hopfield network (CHN) to solve the QP problem. Therefore, the generalized energy function associated with the CHN and an appropriate parametersetting procedure about Max-CSP problems are given in detail. Finally, the proposed algorithm and some computational experiments solving the Max-CSP are shown.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Task assignment problem solved by continuous hopfield network

引用

International Journal of computer Science Issues 2012年第2期9卷 206-212页

作者： Ettaouil, Mohamed Loqman, Chakir Hami, Youssef Haddouch, Khalid UFR: Scientific Computing and Computer sciences Engineering sciences Modeling and Scientific Computing Laboratory Faculty of Science and Technology University Sidi Mohamed Ben Abdellah Box 2202 Fez Morocco Department of Computer Engineering High School of technology Moulay Ismail University B. P. 3103 50000 Toulal Meknes Morocco

The task assignment problem with non uniform communication costs (TAP) consists in finding an assignment of the tasks to the processors such that the total execution and communication costs is minimized. This problem is naturally formulated as 0-1 quadratic programming subject to linear constraints (QP). In this paper, we propose a new approach to solve the task assignment problem with non uniform communication costs using the continuous Hopfield network (CHN). This approach is based on some energy or Lyapunov function, which diminishes as the system develops until a local minimum value is obtained. We show that this approach is able to determine a good solution for this problem. Finally, some computational experiments solving the task assignment problem with non-uniform communication costs are shown. © 2012 International Journal of computer Science Issues.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Learning algorithm of kohonen network with selection phase

引用

WSEAS Transactions on computers 2012年第11期11卷 387-396页

作者： Ettaouil, Mohamed Abdelatifi, Essafi Belhabib, Fatima El Moutaouakil, Karim UFR: Scientific Computing and Computer Sciences Engineering Sciences Modelling and Scientific Computing Laboratory University Sidi Mohamed Ben Abdelah Fez Morocco

The learning algorithm of kohonen network realized away from any notion of class. So, the labelling phase is necessary to find the class associated to data. Generally, the size of the topological map is randomly chosen. Such choice effect the performance of the Kohonen algorithm. Consequently, the labelling phase becomes difficult to realize. To overcome this problem, we add to learning Kohonen algorithm a phase called selection stage. This phase is based on a function called selection function;to construct, we use a sub-set of the data set. In addition, we divided the topological map on two parts: The first contains the used neurons;while the second one is formed by the unused ones. It should be noted that the size of the first and the second parts are modified by the use of the selection function. To compare our method with the classical one, some experiments results are performed.

关键词： Learning algorithms

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：