In neural networks, what are the layers between Input Layer and Output Layer called?

The layers situated between the Input Layer and the Output Layer in neural networks are known as Hidden Layers. These layers are essential components of neural networks, as they are responsible for processing and transforming the data received from the input layer before passing it on to the output layer. Hidden layers contain neurons that apply various activation functions to the weighted input from the previous layer, allowing the network to learn complex patterns and relationships within the data.

The presence and configuration of these hidden layers play a crucial role in the network's ability to make predictions or classifications. The term "hidden" reflects that these layers are not directly exposed to the input or output but serve to enhance the model's learning capability through multiple transformations of the input data.

The other options, while descriptive in their own right, do not accurately represent the established terminology used in the context of neural networks. The term "computational layer" is not commonly used, "cognitive layer" implies functionalities of artificial intelligence that are not specifically layers in a neural network, and "intelligence layer" does not exist as a defined term in the field. Therefore, Hidden Layer remains the accepted terminology for these intermediary layers critical to a neural network's function.