The artificial neuron is another name for the Threshold Logic Unit originally proposed by Warren McCulloch and Walter Pitts in 1940. It is the basic building block of the artificial neural network, simulating a biological neuron. It receives one or more inputs and produces an output based on the calculation of the sum of the inputs using a simple non-linear function as a threshold or step function which is usually a sigmoid.
The artificial neurons are highly interconnected in a large single-layer or multi-layer neural network, the information processing performed in this way may be crudely summarised as follows: signals (action-potentials) appear at the unit's inputs (synapses). The effect each signal has may be approximated by multiplying the signal by some number or weight to indicate the strength of the synapse. The weighted signals are now summed to produce an overall unit activation. If this activation exceeds a certain threshold the unit produces an output response, usually 1 or 0 or 1 and -1.
For a given artificial neuron, let there be n inputs with signals x1 through xn and weights w1 through wn. The signals are Boolean valued, i.e. they take on the values `1' or `0' only. (This allows their relation to digital logic circuitss to be discussed).
The activation u is given by
