Analog Neural Programmable Optimizers in CMOS VLSI Technologies

A 3-μm CMOS IC is presented demonstrating the concept of an analog neural system for constrained optimization. A serial time-multiplexed general-purpose architecture is introduced for the real-time solution of this kind of problem in MOS VLSI. This architecture is a fully programmable and reconfigurable one exploiting SC techniques for the analog part and making extensive use of digital techniques for programmability.