Feed-Forward Network
A fundamental artificial neural network architecture where information travels strictly in one direction from the input layer to the final output layer nodes.
Think of It Like This
Like water flowing down a series of stepped waterfalls; the water always moves forward and never flows backward up the stream to a previous level.
Unlike Recurrent Neural Networks (RNNs), feed-forward networks contain no cycles or feedback loops. They are composed of an input layer, one or more hidden layers, and an output layer. Multi-Layer Perceptrons (MLPs) are the most classic example, serving as foundational building blocks for more complex architectures like transformers.