The first fundamental modeling of neural nets was proposeed in 1943 by McCulloch and Pitts in terms of a computational model of "nervous activity". The McCulloch-Pitts neuron is a binary device and each neuron has a fixed threshold logic. This model lead the works of Jhon von Neumann, Marvin Minsky, Frank Rosenblatt, and many others.
Hebb postulated, in his classical book The Organization of Behavior, that the neurons were appropiately interconnected by self-organization and that "an existing pathway strenghens the connections between the neurons". He proposed that the connectivity of the brain is continually changing as an organism learns different functional tasks, and that cells assemblies are created by such changes. By embedding a vast number of simple neurons in an interactive nervous system, it is possible to provide computational power for very sophisticated informating processing. The neural model can be divided into two categories:
Artificial Neural Networks