Learning structure in temporally-extended sequences is a difficult computational problem because only a fraction of the relevant information is available at any instant. Although variants of back propagation can in principle be used to find structure in sequences, in practice they are not sufficiently powerful to discover arbitrary contingencies, especially those spanning long temporal intervals or involving high order statistics. For example, in designing a connectionist network for music composition, we have encountered the problem that the net is able to learn musical structure that occurs locally in time-e.g., relations among notes within a musical phrase-but not structure that occurs over longer time periods--e.g., relations among phrases. To address this problem, we require a means of constructing a reduced deacription of the sequence that makes global aspects more explicit or more readily detectable. I propose to achieve this using hidden units that operate with different time constants.

The chord skeleton is obtained if eighth and sixteenth notes are viewed as omitable ornamentations. Furthermore, if the chords are conceived as harmonies with certain attributes such as "inversion" or "characteristic dissonances", the chorale is reducible to its harmonic skeleton, a thoroughbass-like representation (Figure 2).

Learning structure in temporally-extended sequences is a difficult computational problembecause only a fraction of the relevant information is available at any instant. Although variants of back propagation can in principle be used to find structure in sequences, in practice they are not sufficiently powerful to discover arbitrary contingencies, especially those spanning long temporal intervals or involving high order statistics. For example, in designing a connectionist network for music composition, we have encountered the problem that the net is able to learn musical structure thatoccurs locally in time-e.g., relations among notes within a musical phrase-butnot structure that occurs over longer time periods--e.g., relations among phrases. To address this problem, we require a means of constructing a reduced deacription of the sequence that makes global aspects more explicit or more readily detectable. I propose to achieve this using hidden units that operate with different time constants.

After being trained on some dozen Bach chorales using error backpropagation, the system is capable of producing four-part chorales in the style of J .s.Bach, given a one-part melody. Our system solves a musical real-world problem on a performance level appropriate for musical practice. HARMONET's power is based on (a) a new coding scheme capturing musically relevant information and (b) the integration of backpropagation and symbolic algorithms in a hierarchical system, combining theadvantages of both. 1 INTRODUCTION Neural approaches to music processing have been previously proposed (Lischka, 1989) and implemented (Mozer, 1991)(Todd, 1989). The promise neural networks offer is that they may shed some light on an aspect of human creativity that doesn't seem to be describable in terms of symbols and rules. Ultimately what music is (or isn't) lies in the eye (or ear) of the beholder.

The following excerpts are from an interview with Marvin Minsky which took place at his home in Brookline, Massachusetts, on January 23rd, 1991. The interview, which is included in its entirety as a Foreword in the book Understanding Music with AI: Perspectives on Music Cognition (edited by Mira Balaban, Kemal Ebcioglu, and Otto Laske), is a conversation about music, its peculiar features as a human activity, the special problems it poses for the scientist, and the suitability of AI methods for clarifying and/or solving some of these problems. The conversation is open-ended, and should be read accordingly, as a discourse to be continued at another time.

An effective to develop an abstract UI model which solution to this problem must have three encompasses the essence of those systems.

We describe a recurrent connectionist network, called CONCERT, that uses a set of melodies written in a given style to compose new melodies in that style. CONCERT is an extension of a traditional algorithmic composition technique in which transition tables specify the probability of the next note as a function of previous context. A central ingredient of CONCERT is the use of a psychologically-grounded representation of pitch.

We describe a recurrent connectionist network, called CONCERT, that uses a set of melodies written in a given style to compose new melodies in that style. CONCERT is an extension of a traditional algorithmic composition technique in which transition tables specify the probability of the next note as a function of previous context. A central ingredient of CONCERT is the use of a psychologically-grounded representation of pitch.

We describe a recurrent connectionist network, called CONCERT, that uses a set of melodies written in a given style to compose new melodies in that style. CONCERT is an extension of a traditional algorithmic composition technique inwhich transition tables specify the probability of the next note as a function of previous context. A central ingredient of CONCERT is the use of a psychologically-grounded representation of pitch.

Commentators on AI converge on two goals they believe define the field: (1) to better understand the mind by specifying computational models and (2) to construct computer systems that perform actions traditionally regarded as mental. We should recognize that AI has a third, hidden, more basic aim; that the first two goals are special cases of the third; and that the actual technical substance of AI concerns only this more basic aim. This third aim is to establish new computation-based representational media, media in which human intellect can come to express itself with different clarity and force. This article articulates this proposal by showing how the intellectual activity we label AI can be likened in revealing ways to each of five familiar technologies.