Creating melodies with evolving recurrent neural networks

Music composition is a domain well-suited for evolutionary reinforcement learning. Instead of applying explicit composition rules, a neural network is used to generate melodies. An evolutionary algorithm is used to find a neural network that maximizes the chance of generating good melodies. Composition rules on tonality and rhythm are used as a fitness function for the evolution. We observe that the model learns to generate melodies according to these rules with interesting variations.

[1]  H. C. Longuet-Higgins,et al.  Perception of melodies , 1976, Nature.

[2]  R. Jackendoff,et al.  A Generative Theory of Tonal Music , 1985 .

[3]  Melissa A. Redford and Chun Chi Chen and Risto Miikkulainen.  Modeling The Emergence Of Syllable Systems , 1998 .

[4]  Michael C. Mozer,et al.  Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing , 1994, Connect. Sci..

[5]  Elliott Antokoletz.  The music of Béla Bartók : a study of tonality and progression in twentieth-century music , 1986 .

[6]  Markand Thakar.  Counterpoint: Fundamentals of Music Making , 1990 .

[7]  R. Douglas Riecken,et al.  WOLFGANG—a system using emoting potentials to manage musical design , 1992 .

[8]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning through Symbiotic Evolution , 1996, Machine Learning.

[9]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[10]  Charles Ames,et al.  Cybernetic composer: an overview , 1992 .

[11]  Elliott Antokoletz.  The Musical Language of Bartók's 14 Bagatelles for Piano , 1981 .

[12]  Ken'ichi Miyazaki.  Perception of Musical Intervals by Absolute Pitch Possessors , 1992 .

[13]  Louis P. DiPalma,et al.  Music and Connectionism , 1991 .

[14]  L. Bernstein.  The Unanswered Question: Six Talks at Harvard , 1977 .

[15]  Peter Desain,et al.  A connectionist and a traditional AI quantizer, symbolic versus sub-symbolic models of rhythm perception , 1993 .