机器学习宣讲.ppt

Click to edit Master title style,Copyright 2009 by Pearson Education,Inc.,Upper Saddle River,New Jersey 07458,All rights reserved.,Neural Networks and Learning Machines,Third Edition,Simon Haykin,Figure 1,Block diagram representation of nervous system.,Figure 2,The pyramidal cell.,Figure 3,Structural organization of levels in the brain.,Figure 4,Cytoarchitectural map of the cerebral cortex.The different areas are identified by the thickness of their layers and types of cells within them.Some of the key sensory areas are as follows:Motor cortex:motor strip,area 4;premotor area,area 6;frontal eye fields,area 8.Somatosensory cortex:areas 3,1,and 2.Visual cortex:areas 17,18,and 19.Auditory cortex:areas 41 and 42.,(From A.Brodal,1981;with permission of Oxford University Press.),Figure 5,Nonlinear model of a neuron,labeled,k,.,Figure 6,Affine transformation produced by the presence of a bias;note that,v,k,=b,k,at,u,k,=,0.,Figure 7,Another nonlinear model of a neuron;,w,k,0,accounts for the bias,b,k,.,Figure 8,(a)Threshold function.(b)Sigmoid function for varying slope parameter,a.,Figure 9,lllustrating basic rules for the construction of signal-flow graphs.,Figure 10,Signal-flow graph of a neuron.,Figure 11,Architectural graph of a neuron.,Figure 12,Signal-flow graph of a single-loop feedback system.,Figure 13,(a)Signal-flow graph of a first-order,infinite-duration impulse response(IIR)filter.(b)Feedforward approximation of part(a)of the figure,obtained by truncating Eq.(20).,Figure 14,Time response of Fig.13 for three different values of feedforward weight,w.,(a)Stable.(b)Linear divergence.(c)Exponential divergence.,Figure 15,Feedforward network with a single layer of neurons.,Figure 16,Fully connected feedforward network with one hidden layer and one output layer.,Figure 17,Recurrent network with no self-feedback loops and no hidden neurons.,Figure 18,Recurrent network with hidden neurons.,Figure 19,Illustrating the relationship between inner product and Euclidean distance as measures of similarity between patterns.,Figure 20,Illustrating the combined use of a receptive field and weight sharing.All four hidden neurons share the same set of weights exactly for their six synaptic connections.,Figure 21,Block diagram of an invariant-feature-space type of system.,Figure 22,Autoregressive model of order 2:(a)tapped-delay-line model;(b)lattice-filter model.(The asterisk denotes complex conjugation.),Figure 23,Doppler-shift-invariant classifier of radar signals.,Figure 24,Block diagram of learning with a teacher;the part of the figure printed in red constitutes a feedback loop.,Figure 25,Block diagram of reinforcement learning;the learning system and the environment are both inside the feedback loop.,Figure 26,Block diagram of unsupervised learning.,Figure 27,Inputoutput relation of pattern associator.,Figure 28,Illustration of the classical approach to pattern classification.,Figure 29,Block diagram of system identification:The neural network,doing the identification,is part of the feedback loop.,Figure 30,Block diagram of inverse system modeling.The neural network,acting as the inverse model,is part of the feedback loop.,Figure 31,Block diagram of feedback control system.,Figure 32,Block diagram of generalized sidelobe canceller.,