hebbian learning meaning in English
赫布型学习
Examples
- This paper aims to combine advantages of pid control and neuron , propose the neuron pid controller which is derived from an incomplete derivative pid algorithm and based on six learning rules in common use , viz . no surpervized hebbian learning rule , perceptron learning rule , supervized learning rule , improved hebbian learing rule , delta learning rule and capability index which is based on second type , and these rules come into being six control arithmatic . then simulate in object with lag
本论文主要将两者的优点结合,提出了神经元实现不完全微分pid ,并采用神经网络常用的六种学习规则,即无监督hebb学习规则、感知器的学习规则、有监督的hebb学习规则、改进的hebb学习规则、 delta学习规则和基于二次型性能指标的学习规则,形成六种控制算法,以工业生产过程中常见的二阶纯滞后对象为例进行仿真。 - In this paper , the artificial neural networks are considered as a structure set of the neurons . based on this point of view , we make a comprehensive and deep researching on the hopfield model neural network of associative memory with hebbian learning in three aspects , i . e . , analyzing , describing and computing of the symmetry of the system , thus discovering the storing mechanism of the hebbian learning rule . which give a deeper understanding to the associative memory mechanism of artificial neural network
本文将人工神经网络视为神经元的结构集，并从这个基本观点出发，从三个方面，即对称性的分析、表示以及计算，对hebb型的离散hopfield模型神经网络进行全面的、深入的研究，揭示了hebb法则这种特殊的存储规则的机理，并以此来达到加深对整个网络的联想记忆机理认识的目的。 - Hi the aspect of symmetry analyzing to the hopfield model neural network with hebbian learning , we study on the dynamical behavior of the state space under the action of isometric transformation group g = z2 ? n , and prove the invariant property of the energy orientation ? / / " ) of the state space under the action of g . we find that the symmetry relationship of the network is sx - sw = sh when the active function of the neuron is odd , where sx is the symmetry of the patterns set x under hebbian learning rule , sh is the symmetry of the network and sw is the symmetry of the weight matrix w of the network
) s _ n为手段，研究了网络状态空间在群g作用下各点的运动情况，证明了群g作用下的不变性。证明了当神经元的激活函数f为奇函数时， hebb法则下存储样本集x的对称性s _ x 、网络对称性s _ h以及连接矩阵对称性s _ w三者之间满足s _ x = s _ w = s _ h的关系；同时，我们还证明了：网络稳定态集vf同一s _ h轨道中的两个稳定态的动力学行为(能量和吸引域大小)相同；两个等距网络h和h 1 = g ? h ， ( ? ) g (