Deep neural networks (DNN)
Introduction to Neural Networks

The main feature of deep neural networks is their large number of hidden layers. There are three main classes of deep neural networks:

• fully connected unidirectional neural networks, also known as artificial neural networks (ANN) or multi-layer perceptrons (MLP);

• convolutional neural networks (CNNs) are unidirectional, with specific layers that perform pre-processing;

• in recurrent neural networks, information can flow in both directions.