In building even the simplest network, we have to make all sorts of choices about network architecture. Should we use 1 hidden layer or 1,000? How many neurons should each layer contain? Should they all use the relu activation function or tanh? Should we use dropout on every hidden layer, or just the first? There are many choices we have to make in designing a network architecture.

In the most typical case, we search exhaustively for optimal values for each hyperparameter. It's not so easy to exhaustively search for network architectures though. In practice, we probably don't have the time or computational power to do so. We rarely see researchers searching for the optimal architecture through exhaustive search because the number of choices is so very vast and because there there is more than one correct answer. Instead, we see researchers in this field building onto known architectures through experimentation to attempt to create new novel architectures and improve existing architectures.

So, before we cover strategies for exhaustively searching hyperparameters, let's look at two strategies for deducing a reasonable, even if not the best, network architecture.