The Single Layer Feed-forward Network is made of a single layer of weight loads, where the inputs are straightly connected to the outputs, via a line of weights. The synaptic links carrying weights join every input to every output, except for other way. This way it can be considered a network of feed-forward variety.

The number of the products of the weights and the inputs is calculated in each neuron node, and if the value is above some minimum threshold (typically 0) the neuron fires and usually takes the activated value (typically 1); otherwise it takes the deactivated value (typically -1).