A neural network is a large, highly interconnected assembly of simple elements. The elements, called neur-ons, are usually two-state devices that switch from one state to the other when their input exceeds a specific threshold value. In this respect the elements resemble biological neurons, which fire—that is, send a voltage pulse down their axons—when the sum of the inputs from their synapses exceeds a “firing” threshold. Neural networks therefore serve as models for studies of cooperat- ive behavior and computational properties of the sort exhibited by the nervous system.
Statistical Mechanics of Neural Networks
Authors: Haim Sompolinsky
Year of publication: 1988
Journal: Physics Today 40, 70. (1988)
Link to publication: