摘要
Hopfield神经网络(HNN)是一种有效的优化模型,但存在易收敛到局部极小的缺点.傅立叶级数具有良好的函数逼近能力和较高的非线性度,基于这一特点,提出了一种新型的Hopfield神经网络——傅立叶Hopfield神经网络(FHNN),其激励函数是由三角函数和S igmoid函数组成,并将该模型用于优化问题.仿真结果表明傅立叶Hopfield神经网络能够较快收敛到最优解,在解决优化问题上表现出令人满意的效果.
Hopfield neural network （HNN） is an efficient optimization model, but it is easy to be trapped in local minima. This paper presents a new model of Hopfield neural network which is called Fourier Hopfield neural network （FHNN） and its activation function is composed by trigonometric function and sigmoid function, based on the fact that the Fourier series not only has the further ability in local approaching but also has a nature of higher nonlinear, and applied the model to the application to optimization problems. The simulation resuits have shown that the Fourier Hopfield neural network has higher ability of searching for globally optimal solutions and summits a satisfied accurate effect in the application of optimization problems.
出处
《哈尔滨商业大学学报（自然科学版）》
CAS
2008年第3期277-280,共4页
Journal of Harbin University of Commerce：Natural Sciences Edition
基金
黑龙江省自然科学基金(F2007-15)
黑龙江省教育厅科学技术一般项目(11521056)
