Neural Networks - Forward Propagation

Neural Networks - Forward Propagation

\(z^{(j)} = \Theta^{(j-1)}a^{(j-1)}\)
\(a^{(j)} = g(z^{(j)})\)
\(h_\Theta(x) = a^{(j+1)} = g(z^{(j+1)})\)

Note the importance of adding a bias term before each forward propagation from one layer to the next

If we're looking at 2 adjacent layers j and j+1 at a time, it is just like logistic regression where features came/result from layer j-1 forward propagation. This allows neural network learns its own features.

Resources:
- https://www.coursera.org/learn/machine-learning/lecture/Hw3VK/model-representation-ii