Can a Niching Method Locate Multiple Attractors Embedded in the Hopfield Network?

机译：努力方法可以定位嵌入在Hopfield网络中的多个吸引器吗？

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

We apply evolutionary computations to the Hopfield's neural network model of associative memory. In the model, a number of patterns can be stored in the network as attractors if synaptic weights are determined appropriately. So far, we have explored weight space to search for the optimal weight configuration that creates attractors at the location of patterns to be stored. In this paper, on the other hand, we explore pattern space to search for attractors that are created by a fixed weight configuration. All the solutions in this case are a priori known. The purpose of this paper is to study the ability of a niching genetic algorithm to locate these multiple solutions using the Hopfield model as a test function.

机译：我们将演化计算应用于Hopfield的关联记忆的神经网络模型。在该模型中，如果适当地确定突触权重，则可以将许多模式存储在网络中作为吸引子。到目前为止，我们已经探索了重量空间来搜索在要存储的模式的位置创建吸引子的最佳权重配置。另一方面，在本文中，我们探索模式空间以搜索由固定权重配置创建的吸引子。在这种情况下所有解决方案都是已知的先验。本文的目的是研究利用遗传算法使用Hopfield模型定位这些多解决方案的能力作为测试功能。

著录项

来源
《Asia-Pacific conference on simulated evolution and learning》|1999年||共8页
会议地点
作者
Akira Imada; Keijiro Araki;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类人工智能理论;
关键词

相似文献

外文文献
中文文献
专利

1. Nonlinear Dynamics of Three-Neurons-Based Hopfield Neural Networks (HNNs): Remerging Feigenbaum Trees, Coexisting Bifurcations and Multiple Attractors [J] . Njitacke Z. T., Kengne J. Journal of Circuits, Systems, and Computers . 2019,第7期

机译：基于三神经元的Hopfield神经网络（HNN）的非线性动力学：Feigenbaum树重新出现，分叉并存和多个吸引子
2. Nonlinear Dynamics of Three-Neurons-Based Hopfield Neural Networks (HNNs): Remerging Feigenbaum Trees, Coexisting Bifurcations and Multiple Attractors [J] . Njitacke Z. T., Kengne J. Journal of Circuits, Systems, and Computers . 2019,第7期

机译：基于三神经元的Hopfield神经网络（HNNS）的非线性动力学：Feigenbaum树的叙述，共存分叉和多个吸引子
3. Complex dynamics of a 4D Hopfield neural networks (HNNs) with a nonlinear synaptic weight: Coexistence of multiple attractors and remerging Feigenbaum trees [J] . Njitacke Z. T., Kengne J. AEU: Archiv fur Elektronik und Ubertragungstechnik: Electronic and Communication . 2018,第期

机译：具有非线性突触重量的4D Hopfield神经网络（HNN）的复杂动态：多个吸引子的共存和默默的费龄树木
4. Can a Niching Method Locate Multiple Attractors Embedded in the Hopfield Network? [C] . Akira Imada, Keijiro Araki Asia-Pacific conference on simulated evolution and learning . 1999

机译：努力方法可以定位嵌入在Hopfield网络中的多个吸引器吗？
5. Robust methods for locating multiple dense regions in complex datasets. [D] . Gupta, Gunjan Kumar. 2006

机译：在复杂数据集中定位多个密集区域的稳健方法。
6. On control of singleton attractors in multiple Boolean networks: integer programming-based method [O] . Yushan Qiu, Takeyuki Tamura, Wai-Ki Ching, 2000

机译：关于多个布尔网络中单例吸引子的控制：基于整数编程的方法
7. An efficient technique based on DORT method to locate multiple soft faults in wiring networks [O] . Kafal, Moussa, Cozza, Andrea, Pichon, Lionel 2016

机译：一种基于DORT方法的高效布线网络故障定位技术
8. Simulation Tests of the Optimization Method of Hopfield and Tank Using Neural Networks [R] . Russell A. Paielli 1988

机译：基于神经网络的Hopfield和Tank优化方法仿真试验

Can a Niching Method Locate Multiple Attractors Embedded in the Hopfield Network?

摘要

著录项

相似文献

相关主题

期刊订阅