Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit

TLDR

The paper proposes using highly interconnected networks of simple analog processors to rapidly solve various optimization problems. The authors design analog‑to‑digital converters and linear‑programming circuits by applying principles of collective computation in interconnected analog‑processor networks. They demonstrate that A/D conversion and linear‑programming problems can be solved by appropriately constructed analog‑processor networks.

Abstract

We describe how several optimization problems can be rapidly solved by highly interconnected networks of simple analog processors. Analog-to-digital (A/D) conversion was considered as a simple optimization problem, and an A/D converter of novel architecture was designed. A/D conversion is a simple example of a more general class of signal-decision problems which we show could also be solved by appropriately constructed networks. Circuits to solve these problems were designed using general principles which result from an understanding of the basic collective computational properties of a specific class of analog-processor networks. We also show that a network which solves linear programming problems can be understood from the same concepts.