Forward propagation in deep networks (part 1)

In this video, we will wrap up what we have learned about forward propagation through deep neural networks and explain how it can be done efficiently for all our training examples $X=\begin{bmatrix} x^{(1)}, x^{(2)}, \dots, x^{(m)}\end{bmatrix}$ in a single pass of forward propagation. As we discuss later, $m$ is often so large that we can only do this for a subset of our training examples at a time, but the principles are still the same.