matlable 人工智能代码（Matlable ai code）.docVIP

matlable 人工智能代码（Matlable ai code） % produces the sample points of the specified category and draws them in the diagram X = [0, 1; 0 1]; Limits the scope of a class center Clusters = 5; Number of specified categories Points = 10; % specify the number of points per class Std_dev = 0.05; Standard deviation per category P = nngenc (X, clusters, points, std_dev); The plot (P (1, :), P (2, :), + r); Title ( input sample vector ); Xlabel ( p (1)); Ylabel ( p (2)); % establishment network Net = newc ([0, 1, 0, 1], 5,0.1); The number of neurons is 5 % get the network weight value and plot it on the graph Figure; The plot (P (1, :), P (2, :), + r); W = net. Iw {1} Hold on. The plot (w (:, 1), w (:, 2), ob); Hold off. Title ( enter the sample vector and the initialization weight ); Xlabel ( p (1)); Ylabel ( p (2)); Figure; The plot (P (1, :), P (2, :), + r); Hold on. % training network Net. TrainParam. Epochs = 7; Net = init (net); Net net = train (P); The value of the network weight after training is obtained and plotted on the diagram W = net. Iw {1} The plot (w (:, 1), w (:, 2), ob); Hold off. Title ( input sample vector and updated weight ); Xlabel ( p (1)); Ylabel ( p (2)); A = 0; [0.6; p = 0.8]; A = sim (.net, p) -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- example8_2 The % randomly generated 1000 two-dimensional vectors as samples and plotted their distribution P = rands (2100); The plot (P (1, :), P (2, :), + r) Title ( initial random sample point distribution ); Xlabel ( P (1)); Ylabel ( P (2)); Network, get the initial weight Net = newsom ([0, 1; 0 1], [5, 6]); W1_init = net. Iw {1, 1} The distribution of the initial weights is plotted Figure; Plotsom (w1_init, net. The layers {1}. The distances) The corresponding weight distribution map is shown in the training network For I = 10:30:10 0 Net. TrainParam. Epochs = I; Net net = train (P); Figure; Plotsom (net. Iw {1, 1}, net. The layers {1}. The distances) The end % for the training network, select a speci