计算智能课件 神经网络.pptVIP

人工神经网络(3) 内容 概率神经网络简介 自组织神经网络 计算智能概论复习要点 概率神经网络 概率神经网络 概率神经网络 许多研究已表明概率神经网络具有以下特性： (1)训练容易，收敛速度快，从而非常适用于实时处理； (2)可以完成任意的非线性变换，所形成的判决曲面与贝叶斯最优准则下的曲面相接近； (3)具有很强的容错性； (4)模式层的传递函数可以选用各种用来估计概率密度的核函数，并且，分类结果对核函数的形式不敏感； (5)各层神经元的数目比较固定，因而易于硬件实现； 这种网络已较广泛地应用于非线性滤波、模式分类、联想记忆和概率密度估计当中。 概率神经网络 概率神经网络 概率神经网络 概率神经网络 Unsupervised learning The main property of a neural network is an ability to learn from its environment, and to improve its performance through learning. So far we have considered supervised or active learning - learning with an external “teacher” or a supervisor who presents a training set to the network. But another type of learning also exists: unsupervised learning. Hebbian learning In 1949, Donald Hebb proposed one of the key ideas in biological learning, commonly known as Hebb’s Law. Hebb’s Law states that if neuron i is near enough to excite neuron j and repeatedly participates in its activation, the synaptic connection between these two neurons is strengthened and neuron j becomes more sensitive to stimuli from neuron i. Hebb’s Law can be represented in the form of two rules (1) If two neurons on either side of a connection are activated synchronously, then the weight of that connection is increased. (2) If two neurons on either side of a connection are activated asynchronously, then the weight of that connection is decreased. Hebb’s Law provides the basis for learning without a teacher. Learning here is a local phenomenon occurring without feedback from the environment. Hebbian learning in a neural network Hebbian learning in a neural network Hebbian learning in a neural network Hebbian learning algorithm Hebbian learning algorithm Hebbian learning example Initial and final states of the network Initial and final weight matrices Hebbian learning example Competitive learning In competitive learning, neurons compete among themselves to be activated. While in Hebbian learning, several output neurons can