% P. 145 - Backpropagation for XOR (Sivanandam) p = [0 0 1 1; 0 1 0 1]; % Input t = [0 1 1 0]; % Target (XOR) % Create network (MATLAB 6.0 style) net = newff(minmax(p), [2 1], {'tansig' 'purelin'}, 'traingd');
% Train and simulate net = train(net, p, t); out = sim(net, p); disp('Output:'); disp(out); net.trainParam.lr = 0.5
In the rapidly evolving landscape of artificial intelligence, where TensorFlow, PyTorch, and Keras dominate the headlines, it is easy to forget the foundational texts that built the modern discipline. One such cornerstone, often whispered about in university corridors and on specialized technical forums, is the book "Introduction to Neural Networks Using MATLAB 6.0" by S. N. Sivanandam, S. Sumathi, and S. N. Deepa. net.trainParam.goal = 0.001
% Set parameters net.trainParam.epochs = 1000; net.trainParam.lr = 0.5; net.trainParam.goal = 0.001; 0 1 0 1]