$3$ CNN for Classification of Synthetic Data

Let's start attempting to differentiate between your two synthetic images using a simple CNN archi$-$

tecture. The CNN architecture is as follows. All hyperparameter choice are up to you:

A single $99$ convolutional kernel.

A max$-$pool layer with width $=4$ and stride $=4.$

A flattened layer

A Fully Connected Layer

A Logistic Sigmoid activation function

A Log Loss objective function.

What you will need for your report

Image representations of your initial and final kernels.

A plot of the log loss as a function of the number of iterations.

Your hyperparameter choices.