Affine layers are fully connected layers in neural networks, where affine can be seen as the interconnections between neurons in different layers, and in many ways can be seen as the "standard" layer of a neural network.

The general form of an affine layer is as follows

y = f(wx + b)

Note: x is the layer input, w is the parameter, b is a bias vector, and f is a non-linear activation function.

Affine layers are often used as the final layer at the output of a convolutional neural network or a recurrent neural network.