Neural Network Programming
Loading ... Neural Network Programming Business claims
"MATLAB neural network programming" is edited by Zhang Defeng, Chemical Industry Publishing House published books.
Edit Summarytable of Contents
Basic Information / MATLAB Neural Network Programming Editing
Introduction / MATLAB Neural Network Programming Editing
"MATLAB neural network programming" combined with the concept, theory and application of neural network to MATLAB as a platform, the system introduced the neural network toolbox in the forward neural network, local neural network, feedback neural network, competitive nerve Neural network control, the application of neural network in Simulink, the fuzzy control of neural network and its self-defined network and so on. "MATLAB neural network programming" focuses on the use of MATLAB neural network toolbox introduced neural network analysis of the various concepts, theories, methods, algorithms and their implementation. "MATLAB neural network programming" content arrangement is reasonable, theory and practice, at the same time the author lists a large number of examples of its summary. "MATLAB neural network programming" tells a variety of statistical theory and methods are easy to understand, and can be found in real life applications. "MATLAB neural network programming" can be used as the majority of undergraduates and graduate students in learning books, but also as the majority of scientific research personnel, academics, engineering and technical personnel reference books.
Neural Network Programming Editing
The 1st chapter MATLAB ABC 1.1The overview of MATLAB 1.1.1 The development history of MATLAB and influence 1.1.2Functional characteristic of MATLAB 1.1.3The new characteristic of MATLABR2010a 1.2The preliminary application of MATLAB 1.2.1The start and shut of MATLAB 1.2.2The tool of MATLAB And the menu 1.2.3 MATLAB command window 1.2.4 MATLAB workspace 1.2.5 MATLAB command history window 1.2.6 MATLAB's current directory 1.3 MATLAB variables and symbols 1.3.1 special variables 1.3.2 punctuation 1.4 vector creation method 1.4.1 direct input method 1.4.2 use colons to generate a law 1.4.3 use function generate a method 1.4.4 vectors are connected law of 1.5 matrixes 1.5.1 build of matrix 1.5.2 matrix break up 1.6 matrix element arrangement and Replace 1.6.1 Index and index 1.6.2 elements of the extraction and replacement 1.6.3 matrix row and column-related operations 1.6.4 end function of the use of 1.7 matrix and array of basic operations 1.7.1 matrix and array operations 1.7. 2 matrices 1.8 MATLAB help function 1.8.1 help command 1.8.2 inquiry order 1.8.3 online help 1.8.4 demonstrate help The 2nd chapter MATLAB basic program and drawing function 2.1 MATLAB control statement 2.1.1 condition control 2.1.2 cycle control 2.1.3 program flow control 2.2 M file 2.2.1 script file 2.2.2 M function 2.3 two-dimensional graphics 2.3.1 basic two-dimensional graphics function 2.3.2 line type, point type, color 2.3. 3 window control 2.3.4 coordinate axis control 2.3.5 graphic annotation 2.4 three-dimensional graph 2.4.1 three-dimensional curve drawing 2.4.2 three-dimensional surface drawing The 3rd chapter neural network introduction 3.1 artificial neural network concept put forward 3.2 The development history of artificial neural network and The content of the research 3.2.1 Artificial neural network history 3.2.2 Artificial neural network content of the study 3.3 The composition of neurons and artificial neurons 3.4 Artificial neuron model 3.5 Neuron structure 3.6 Neural network characteristics and advantages of 3.7 Artificial neurons 3.8 Artificial neurons and artificial intelligence 3.8.1 Overview of artificial intelligence 3.8.2 Artificial neurons and artificial intelligence comparison 3.9 Using MATLAB to calculate the output of artificial neural network Chapter 4 of the forward neural network 4.1 Sensor network 4.1.1 The structure of perceptron 4.1.2 Perceptron learning 4.1.3 Limitations of perceptron 4.1.4 The "foreign problem" of perceptron 4.1.5 Neural network training function of perceptron 4.1.6 Realization of perceptron network 4.1.7 linear classification of the expansion of the discussion 4.1.8 linear separable solution 4.2 linear neural network 4.2.1 linear neural network model 4.2.2 WH learning rules 4.2.3 linear neural network training function 4.2.4 linear Neural network construction 4.2.5 network training 4.2.6 linear neural network implementation 4.2.7 linear neural network limitations 4.2.8 system identification 4.3 BP propagation network 4.3.1 BP network model structure 4.3.2 BP learning rules 4.3. 3 The training function of BP network 4.3.4 The realization of BP network 4.3.5 Restriction of BP network 4.3.6 The improvement of BP method Chapter 5 Local neural network 5.1 Radial basis function network 5.1.1 Radial neuron and radial Based network model 5.1.2 Radial Basis Function Network Learning Algorithm 5.1.3 Generalized Regression Neural Network 5.1.4 Radial Basis Function Network Training Function 5.1.5 Radial Basis Function Network Implementation 5.1.6 Based on RBF network Nonlinear filtering 5.1.7 Comparison of RBF network and multi-layer perceptron 5.2 B-spline basis function 5.3 Probabilistic neural network 5.3.1 PNN network structure 5.3.2 PNN network working principle 5.3.3 PNN network design 5.4 CMAC network 5.4 .1 CMAC network structure 5.4.2 CMAC learning algorithm 5.5 GMDH network 5.5.1 GMDH network overview 5.5.2 GMDH network training 5.6 CMAC, B spline and RBF similarities and differences 5.6.1 CMAC, B spline and RBF Of the same 5.6.2 CMAC, B-spline and RBF differences Chapter 6 feedback neural network 6.1 Hopfield network 6.1.1 Discrete Hopfield network 6.1.2 continuous Hopfield network 6.1.3 associative memory 6.1.4 Hopfield network Structure 6.1.5 Hopfield network model learning process 6.1.6 several important conclusions 6.1.7 Application of Hopfield network 6.2 Elman network 6.2.1 Elman network structure 6.2.2 revise the weight algorithm of network weight 6.2.3 stability derivation 6.2. 4 Diagonal recursive network to determine the stability of the learning rate 6.2.5 Elman network and training 6.2.6 Elman network applications 6.3 Bi-directional associative memory network 6.3.1 BAM network structure and principle 6.3.2 Energy function and stability analysis 6.3.3 BAM network weight design 6.3.4The application of BAM network The 6.4 box is in the brain model 6.4.1The box is described in the brain model 6.4.2 The box is in the brain model to realize 6.5 Local recurrent neural network 6.5.1 PIDNNC is designed 6.5.2 Closed-loop control system stability analysis The 7th chapter competitive neural network 7.1 self-organizing neural network basic function 7.1.1 found a function 7.1.2 study function 7.1.3 competition transfer function 7.1.4 initialization function 7.1.5 distance function 7.1.6 Training competition layer function 7.1.7 drawing function 7.1.8 structure function 7.2 self-organizing competition neural network 7.2.1 commonly used several kinds of association learning rules 7.2.2 self-organizing competition neural network structure 7.2.3 self-organizing competition neural network design 7.2.4 Application of self-organizing competitive neural network 7.3 Self-organizing feature mapping network 7.3.1 Self-organizing feature mapping network model 7.3.2 Structure of self-organizing feature mapping network 7.3.3 Design of self-organizing feature mapping network 7.3.4 Self- Application of characteristic mapping network 7.4 learning vector quantization neural network 7.4.1 learning vector quantify the structure of neural network 7.4.2 learning vector quantization of learning of neural network 7.4.3 learning vector quantization of learning algorithm improvement 7.4.4 learning vector quantization neural network The application 7.5 The principal component analysis 7.5.1 The principal component analysis method 7.5.2 The principal component analysis network algorithm 7.5.3 Nonlinear principal component analysis and its network model The 8th chapter neural network control synthesis application 8.1 Neural network control structure 8.1. 1 neural network supervisory control 8.1.2 neural network predictive control 8.1.3 neural network adaptive judgment control 8.2 minimum variance self-correcting control 8.2.1 minimum variance control 8.2.2 minimum variance indirect self-correcting control 8.2.3 minimum variance direct self-tuning Control 8.3 model predictive control 8.3.1 system identification 8.3.2 generalized predictive control 8.4 crop crop predicting 8.4.1 based on the neural network forecasting principle 8.4.2 BP network design 8.5 model reference control 8.5.1 model reference control concept 8.5 .2 model reference control case analysis 8.6 neural network control application 8.6.1 robot neural network digital control 8.6.2 neural network tracking iterative learning control neural network in Chapter 9 of the application of Simulink 9.1 Simulink interactive simulation integrated environment 9.1. 1 Simulink model establishment 9.1.2 Simulink simulation 9.1.3 Simulink simple example 9.2 Simulink neural network module 9.2.1 transfer function module 9.2.2 network input module 9.2.3 weight value sets up a module 9.2.4 control system module 9.3 Simulink application example Chapter 10 neural network fuzzy control and its own definition of the network 10.1 neural network fuzzy control 10.1.1 neural network control structure 10.1.2 neural network characteristics 10.1.3 neural network fuzzy controller application 10.1.4 neural network fuzzy The control applies to the washing machine 10.2 neural networks custom network 10.2.1 custom network 10.2.2 network design 10.2.3 network training References
Fig
upload imageAdd a video | add an image
Open up the classification of open classificationInteractive Wikipedia entry (with pictures attached) by the users, if the alleged infringement, please contact customer service, we will be in accordance with the relevant provisions of the law in time for processing. Unauthorized, prohibit commercial sites such as copy, crawl the site reasonable use, please specify from www.baike.com.
Login to use interactive services, will be personalized tips and help, as well as opportunities and professional certification of volunteers to communicate.
You can also add information modules
Comments
Post a Comment