Abstract
Adaptive production systems are defined and used to illustrate adaptive techniques in production system construction. A learning paradigm is described within the framework of adaptive production systems, and is applied to a simple rote learning task, a nonsense syllable association and discrimination task, and a serial pattern acquisition task. It is shown that with the appropriate production building mechanism, all three tasks can be solved using similar production system learning techniques. The adaptive production systems are quite parsimonious; that is, the learning program is represented in exactly the same fashion as the information being learned. Both are represented as production rules in a single production system. This eliminates the need for two types of control in the system; one for activating the learning mechanism and another for accessing the information learned.