模式识别与人工智能之十一课件.ppt

Pattern Recognition artificial Intelligence Lecture 11: 聚类算法（七） 1 Artificial Neural Networks Biological and artificial networks Competitive Learning Networks Competitive Learning Self-Organizing Map (SOM) Adaptive Resonance Theory (ART) Relationship between K-means, FCM and Competitive Learning Network   Model-based clustering (2) 2 Biological and artificial networks 3 Biology： Biological and artificial networks 4 Artificial The artificial neural network is a group of neurons organized in several layers: Input layer: receives inputs from sources external to the network; Output layer: generates outputs to the external world. Hidden layer(s): layers in between of the input and output layers, not visible from outside the network. Learning laws: mathematical rules for modifying the weights of a network iteratively according the inputs (and outputs if the learning is supervised). Biological and artificial networks 5 Mathematical Explanation A neuron is modeled mathematically as the following: Activation - the net input signal: The net input to the ith node is a weighted sum of all inputs: Where is the input signal from the jth node, is the synaptic connectivity between the jth node and the ith node. Biological and artificial networks 6 Mathematical Explanation Output signal: The output of the ith node is a function of the net input  Where is an activation function which can be a sigmoid function, as plotted in the figure below. This function can be either one-sided (top) or two-sided (bottom) : Biological and artificial networks 7 Mathematical Explanation One-sided: Two-sided: where is a parameter that controls the slop of Specially, when becomes linear, but when becomes a threshold function: Biological and artificial networks 8 Mathematical Explanation Curve of Sigmoid function Competitive Learning Networks 9 C