RULE-BASED ADAPTIVE CONFIGURATION SELECTION FOR ANALOG DESIGN SYSTEMS

A configuration selection tool for rule-based analog IC design is pres ented. A fast determination of proper analog circuit configuration pla ys an eminent role in the initial design phase. This appears to be qui te demanding due to the large number of parameters and side issues inv olved. In order to ease concept engineering in analog design an adapti ve algorithm has been developed for configuration selection. It can be used in design systems that rely on use of expert knowledge stored as a set of rules in a knowledge base, e.g., expert systems, design assi stants, etc. The developed learning algorithm also helps eliminate inc onsistent, incorrect, and redundant rules in rule bases used in analog design systems. The rule base is continuously adapted, depending on t he correctness of the decisions the rules have invoked.