In neural networks, the first layer is connected to the input values, called the “input layer.” The output of the final layer corresponds to a prediction about some objective, called the “output layer.”
All of the layers in between the input and the output layers are called hidden layers. Here, the term “hidden” derives from hidden Markov models. It refers to the fact that these values don’t refer to any directly observable facts; they are learned, latent properties of the system.