Basic Steps for Using Gradient Descent (Step 0 and 1)
Explore the initial steps of using gradient descent by understanding how to randomly initialize model parameters and perform the forward pass to compute predictions. This lesson helps you grasp why random guesses are necessary and how predictions start before training improves them.
We'll cover the following...
We'll cover the following...
Step 0 - Random initialization
In our example, we already know the true values of the parameters, but this will obviously never happen in real life. If we knew the true values, why even bother to train a model to find them?
Given that we will never know the true values of the parameters, we need to set ...