Exercise

L2-regularization

You are going to implement each of the regularization techniques explained in the previous video. Doing so, you will also remember important concepts studied throughout the course. You will start with l2-regularization, the most important regularization technique in machine learning. As you saw in the video, l2-regularization simply penalizes large weights, and thus enforces the network to use only small weights.

Instructions

100 XP

Instantiate an object called model from class Net(), which is available in your workspace (consider it as a blackbox).
Instantiate the cross-entropy loss.
Instantiate Adam optimizer with learning_rate equals to 3e-4, and l2 regularization parameter equals to 0.001.