Artificial Neural Network in Matlab
اسلاید 1: Artificial Neural Network in MatlabHany Ferdinando
اسلاید 2: Neural Network in Matlab2Architecture (single neuron)w is weight matrices, dimension 1xRp is input vector, dimension Rx1b is biasa = f(Wp + b)
اسلاید 3: Neural Network in Matlab3Transfer Function
اسلاید 4: Neural Network in Matlab4Architecture with neuronsw is weight matrices, dimension SxRp is input vector, dimension Rxnb is bias
اسلاید 5: Neural Network in Matlab5Multiple layers
اسلاید 6: Neural Network in Matlab6Perceptrons in MatlabMake the perceptrons with net = newp(PR,S,TF,LF)PR = Rx2 matrix of min and max values for R input elementsS = number of output vectorTF = Transfer function, default = ‘hardlim’, other option = ‘hardlims’LF = Learning function, default = ‘learnp’, other option = ‘learnpn’learnp Dw = (t-a)pT = epTlearnpn normalized learnphardlim = hardlimit functionhardlims = symetric hardlimit functionWnew = Wold + DWbnew = bold + ewhere e = t - a
اسلاید 7: Neural Network in Matlab7Compute manually…This is an exercise how to run the artificial neural networkFrom the next problem, we will compute the weights and biases manually
اسلاید 8: Neural Network in Matlab8AND Gate in PerceptronP = [0 0 1 1; 0 1 0 1];T = [0 0 0 1];net = newp([0 1; 0 1],1);weight_init = net.IW{1,1}bias_init = net.b{1}net.trainParam.epochs = 20;net = train(net,P,T);weight_final = net.IW{1,1}bias_final = net.b{1}simulation = sim(net,P)weight_init = [0 0], bias_init = 0weight_final = [2 1], bias_final = -3
اسلاید 9: Neural Network in Matlab9OR Gate in PerceptronP = [0 0 1 1; 0 1 0 1];T = [0 1 1 1];net = newp([0 1; 0 1],1);weight_init = net.IW{1,1}bias_init = net.b{1}net.trainParam.epochs = 20;net = train(net,P,T);weight_final = net.IW{1,1}bias_final = net.b{1}simulation = sim(net,P)weight_init = [0 0], bias_init = 0weight_final = [1 1], bias_final = -1
اسلاید 10: Neural Network in Matlab10NAND Gate in PerceptronP = [0 0 1 1; 0 1 0 1];T = [1 1 1 0];net = newp([0 1; 0 1],1);weight_init = net.IW{1,1}bias_init = net.b{1}net.trainParam.epochs = 20;net = train(net,P,T);weight_final = net.IW{1,1}bias_final = net.b{1}simulation = sim(net,P)weight_init = [0 0], bias_init = 0weight_final = [-2 -1], bias_final = 2
اسلاید 11: Neural Network in Matlab11NOR Gate in PerceptronP = [0 0 1 1; 0 1 0 1];T = [1 0 0 0];net = newp([0 1; 0 1],1);weight_init = net.IW{1,1}bias_init = net.b{1}net.trainParam.epochs = 20;net = train(net,P,T);weight_final = net.IW{1,1}bias_final = net.b{1}simulation = sim(net,P)weight_init = [0 0], bias_init = 0weight_final = [-1 -1], bias_final = 0
اسلاید 12: Neural Network in Matlab12Backpropagation in MatlabMake the backpropagation with net = newff(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF)PR = Rx2 matrix of min and max values for R input elementsS = number of output vectorBTF = Transfer function (user can use any transfer functions)BLF = Learning functionPF = performancexk+1 = xk - akgk
اسلاید 13: Neural Network in Matlab13Linear Filter (with ANN) in MatlabMake the Linear Filter with newlin(PR,S,ID,LR)PR = Rx2 matrix of min and max values for R input elementsS = number of output vectorID = delayLR = Learning RateTransfer function for linear filter is only linear line (purelin)
نقد و بررسی ها
هیچ نظری برای این پاورپوینت نوشته نشده است.