Abstract: An Integrated Circuit with an automatically re-tuning analog circuit is provided. The Integrated Circuit comprises (a) an analog circuit comprising a plurality of tunable components each configured to respond to a plurality of change control bits, (b) a Process, Voltage Temperature (PVT) characteristics monitor comprising a plurality of PVT sensors, (c) a tuning memory embedded with a machine learning (ML) model of the analog circuit and (d) an artificial intelligence (AI) engine configured to receive a PVT signal input from the plurality of PVT sensors and the machine learning model embedded in the tuning memory. Each tunable component is configured to change its electrical characteristics such that together each of the tunable components is enabled to retune the analog circuit to attain a predefined set of electrical characteristics.

Abstract: The present description relates to a method based on artificial intelligence to implement a wide range of microelectronic circuits that can adapt by themselves to the usage conditions (e.g. loading changes), manufacturing variances or defects (e.g. process variations, device parameter mismatches, device model inaccuracies or changes, etc.), as well as environmental conditions (e.g. voltage, temperature, interference) in order to negate all or part of their effects on the circuit performance characteristics and achieve a very tight set of specifications over the wide range of conditions. Each microelectronic circuit is represented by a neural network model whose behavior is a function of the actual input signals, the usage and environmental conditions.

Abstract: The present description relates to a method based on artificial intelligence to implement a wide range of microelectronic circuits that can adapt by themselves to the usage conditions (e.g. loading changes), manufacturing variances or defects (e.g. process variations, device parameter mismatches, device model inaccuracies or changes, etc.), as well as environmental conditions (e.g. voltage, temperature, interference) in order to negate all or part of their effects on the circuit performance characteristics and achieve a very tight set of specifications over the wide range of conditions. Each microelectronic circuit is represented by a neural network model whose behavior is a function of the actual input signals, the usage and environmental conditions.