Learning syntactically significant temporal patterns of chords: A masking field embedded in an ART 3 architecture

In the traditional harmonic syntax of classical music, temporal patterns of chords vary in length, they often nest one within another, and they may lack overt markers indicating pattern boundaries. The self-organized learning of such patterns can be accomplished by a masking field embedded in an ART 3 architecture. A simulation of learning the chord patterns in the music of Handel uses a dynamic short-term memory store to transform sequential patterns of chords into network patterns of activation. A masking field develops distributed recognition codes for those patterns. Some suggestions are offered for implementing masking fields within the ART 3 architecture.