The textbook speaks extensively of Log-Sigmoid ( logsig ) and Tan-Sigmoid ( tansig ). In modern frameworks, these map directly to sigmoid and tanh activations, alongside newer options like ReLU (Rectified Linear Unit).
To understand why studying Sivanandam's text is still valuable, it helps to see how the syntax of MATLAB 6.0 compares conceptually to modern Python equivalents like TensorFlow/Keras. Legacy MATLAB 6.0 Syntax Modern Python (Keras) Equivalent The textbook speaks extensively of Log-Sigmoid ( logsig
The core concepts (feedforward, backprop, regularization) have not changed. Once you learn with MATLAB 6.0, migrating to MATLAB 2025’s Deep Learning Toolbox is trivial. The textbook speaks extensively of Log-Sigmoid ( logsig