The book utilizes the Neural Network Toolbox to solve application examples in fields like bioinformatics, robotics, and image processing. Typical workflows described include:
| Old MATLAB 6.0 (PDF) | Modern MATLAB (2024) | Explanation | | :--- | :--- | :--- | | newff(minmax(P), [5 1], 'tansig' 'purelin', 'trainlm') | feedforwardnet([5 1]) | The architecture is now encapsulated in feedforwardnet . | | train(net, P, T) | net = train(net, P, T) | You must assign the output back to the network. | | sim(net, P_test) | net(P_test) | You can now call the network as a function directly. | | init(net) | net = init(net) | Similar assignment requirement. | | learnbp (manual backprop) | Obsolete; use train with 'traingd' | The toolbox has automated this. | introduction to neural networks using matlab 6.0 .pdf
This is where the PDF shines. Before automatic differentiation, you had to understand the chain rule. The MATLAB 6.0 implementation forces you to choose: The book utilizes the Neural Network Toolbox to
MATLAB 6.0 had excellent 2D plotting. The PDF extensively uses plotpv (plot perceptron input vectors) and plotpc (plot perceptron classification line). For a beginner, watching the decision boundary animate during training is a revelatory experience. | | sim(net, P_test) | net(P_test) | You