Feed-Forward Neural Networks (FFNN)

It's an Artificial Neural Networks (ANN) architecture, in which the information flows in only one direction, from the input layer to the output layer. FFNNs can store information in context nodes, allowing it to learn data represent sequences and output a number or another sequence.


  • Applications in Classification and Regression.
  • They are usually trained through back-propagation and Supervised Learning.
  • In a Fully-Connected Feed-Forward network, each neuron receives input from every element of the previous layer and thus the receptive field of a neuron is the entire previous layer. This type of feed-forward network is computationally expensive to train.