2012/10/25 Introduction to MATLAB Neural Network Toolbox Static Neural Networks 2012/10/22 1 How to Use Neural Network Toolbox M-file Editor or Command Window Graphical User Interface (GUI) >> nntool Simulink >> Neural Network Toolbox 2 1 2012/10/25 Basic Concept Date collection: Training data Testing data x1 Network creation: w1 x2 w2 Axon Static networks Dynamic networks … Output No. of parameters: wn xn Activation function (Cell body) Synaptic weights Hidden layers, neurons, … Desired Output u System Training parameters: y Epochs, learning rate, … Training Testing 3 Data Preprocessing & Postprocessing Normalization formula: Y Ymin (Ymax Ymin ) (X Xmin ) / (Xmax Xmin ) Process matrices by mapping row minimum and maximum values to [Ymin, Ymax] Syntax: mapminmax >>[Y, PS]=mapminmax(X); PS: Process settings that allow consistent processing of values >>[Y, PS]=mapminmax(X, Ymin, Ymax); >>X=mapminmax(‘reverse’, Y, PS); 4 2 2012/10/25 Neural Network Models 1. Perceptron 2. Linear Filters 3. Backpropagation 4. Radial Basis Networks 5. Competitive Networks 6. Learning Vector Quantization Network 7. Recurrent Networks 8. NARX Networks 5 Transfer Function Graphs 6 3 2012/10/25 Learning Algorithms 7 Feedforward Neural Networks Scalar: a, b, c; Vector: a, b, c; Matrix: A, B, C; P (r×N): Input data (r: No. of input elements, N: No. of input patterns) T (m×N): Output data (m: No. of output elements) n: nth layer, including the hidden and output layers IWk, l: Input weight matrix (lth input set to kth layer) LWk, l: Layer weight matrix (lth layer to kth layer) 8 4 2012/10/25 Feedforward Neural Networks 9 Feedforward Neural Networks Syntax: newff net = newff(P, T, [S1 … S(n-1)], {TF1 … TFn}, BTF) Si: Size of ith layer, for N-1 layers. (Default = [].) TFi: Transfer function of ith layer. (Default = ‘tansig’ for hidden layers and ‘purelin’ for output layer.) BTF: Backpropagation network training function (Default = ‘trainlm’) 10 5 2012/10/25 Feedforward Neural Networks Example 1: t = abs(p) Training input data: P = [0 -1 2 -3 4 -5 6 -7 8 -9 10]; Training output data: T = [0 1 2 3 4 5 6 7 8 9 10]; >>clc; clear all; close all; >>% Collect data >>P = [0 -1 2 -3 4 -5 6 -7 8 -9 10]; >>T = [0 1 2 3 4 5 6 7 8 9 10]; >>% Create network >>net = newff(P,T,10); >>net >>% Training >>net = train(net, P, T); >>% Testing >>y = sim(net,P); >>% Error >>error = mse(y-T) 11 Feedforward Neural Networks 12 6 2012/10/25 Train Feedforward Neural Networks Set training parameter values: net.trainParam >>net.trainParam.epochs = 100; >>net.trainParam.show = 25 or NaN; >>net.trainParam.lr = 0.01; >>net.trainParam.goal = 0; Train the network >>[net, tr] = train(net, P, T); Simulate or test the network >>y = sim(net, Pt); Testing input data: Pt = [0 1 -2 3 -4 5 -6 7 -8 9 -10]; Testing output data: Tt = [0 1 2 3 4 5 6 7 8 9 10]; 13 Graph User Interface (GUI) >>nntool 14 7 2012/10/25 Practice 1 Please create a feedforward neural network and to perform the iris classification problem. Show the network structure and all learning results including the learning curves with different user-specified parameters for training and test data, the train parameters, the resulted membership functions, and/or the weight changes. Show the recognition results for the neural network. The training/testing data are available on the course website (http://140.116.215.51) ‘practice1.mat’ include: P (4x135) T (1x135) Pt (4x15) Tt (1x15) 15 16 8
© Copyright 2024