Neural network refinements and extensions
John S. Denker · AIP conference proceedings · 1986
This paper contains some ideas for tidying up and extending the standard neural network model. It includes some fundamental generalities as well as some arcane technicalities. One central theme is how to make a network that is as close to ideal as possible, given various restrictions on the available fabrication resources. Another theme is how to understand not only the statics but also the dynamics of the network.