ABSTRACT
This chapter describes the National Bureau of Standards’s The Cerebellar Model Articulation Controller (CMAC), relating the context in which the publication appeared, its impact on science, technology, and the general public, and brief details about the lives and work of the author. CMAC is a kind of memory, or table look-up mechanism, that is capable of learning motor behavior. It exhibits properties such as generalization, learning interference, discrimination, and forgetting that are characteristic of motor learning in biological creatures. CMAC modules are designed to accept both input command variables from higher levels and feedback variables from sensors. Each CMAC merges these two inputs into a set of memory addresses wherein are stored the correct motor response. CMAC learns correct output responses for various input conditions by modifying the contents of the selected memory locations. CMAC modules are specifically designed to be integrated into a hierarchy wherein tasks are decomposed into subtasks at each level.
