Bicameral neural network where information can be indexed
Subhash C. Kak, Michael Stinson · Electronics Letters · 1989
A new neural network model that uses an asynchronous controller in the feedback loop is described. The proposed asynchronous controller together with the basic neural net forms a bicameral network that can be programmed in various ways to exploit global and local characteristics of stored memory. It is shown that memories can be indexed and ordered. The central result of the letter is that a memory can be retrieved based on its indexing key alone.