Computer%20Music%20Generation:%20NEAT%20Drummer

1
Computer Music Generation NEAT Drummer

• Presentation by Amy Hoover
• (Based on Paper, Reference 1)
• COT 4810
• 03/04/08

2
Introduction

• Music composers can hear simultaneous parts
• Sounds artificial
• Idea Different instrument parts may be
  functionally related
• Melody may be a scaffold, i.e. an existing
  support structure
• Implementation NEAT Drummer generates drum
  patterns for human compositions

3
Outline

• Background
• Neural Networks
• Musical Instrument Digital Interface
• Interactive Evolutionary Computation
• NEAT Drummer
• Generated drum tracks
• Discussion
• Conclusion

4
Neural Networks
Artificial Neural Network (ANN)
Biological
Output
Output
Input
Input
5
ANNs

• ANN Activation

Neuron j activation
out1
out2
H1
H2
w11
w21
w12
X1
X2
6
Musical Instrument Digital Interface

• Basic MIDI file

Track 1
Track 3
Track 2
Piano
Piano
Piano
Fiddle
Guitar
Fiddle
Banjo
Bass
Banjo



7
Interactive Evolutionary Computation

• Interactive evolutionary computation (IEC) The
  user selects the parents of the next generation
• Original idea Biomorphs (Dawkins, 1987)
• First musical implementation Sonomorphs (Nelson,
  1993)

(Nelson, 1993)
(Dawkins, 1987)
8
IEC Example Picbreeder

• http//picbreeder.org

9
IEC Example Picbreeder
http//picbreeder.org
10
IEC Example Picbreeder

• NEAT Drummer uses the
• same algorithm and encoding

http//picbreeder.org
11
Encoding Compositional Pattern Producing
Networks (CPPNs)

• CPPN a type of ANN
• Activation functions arent restricted to typical
  ANN sigmoids
• Can include sine, Gaussian, others

12
Encoding Compositional Pattern Producing
Networks (CPPNs)

• Designed to produce regularities

DAmbrosio
13
Connectionist Music

• Most connectionist music encodes recurrent ANNs
• Evolving recurrent ANNs (Chen and Miikkulainen,
  2001)
• Current problem either evolve to fit style or
  artificial

14
NEAT Drummer

• Generates drum patterns for existing human
  compositions
• Drum patterns represented by CPPN output values
  over time
• Evolved with NEAT

15
Evolving CPPNs Interactively

• Generate random initial population
• Evolve increasingly complex rhythms through user
  guided selection

16
How CPPNs Encode Drum Tracks
17
Experiments Adding Drum Tracks

• Add drum tracks to two popular folk songs
• Originally sequenced by Barry Taylor without
  drums (added drums with permission)
• Songs Johnny Cope, Oh! Susanna
• Show power of functional relationship

18
NEAT Drummer
19
Johnny Cope

• Even first generations sound good
• Not truly random

20
Johnny Cope

• Even first generations sound good
• Not truly random

21
Johnny Cope

• Even first generations sound good
• Not truly random

22
Johnny Cope

• Even first generations sound good
• Not truly random

23
Oh! Susanna
24
Oh! Susanna
25
Oh! Susanna
26
Discussion and Future Work

• Functional relationship is the right
  representation for relating parts of a song
• What is the right language for encoding music?
  Not music?
• No need for recurrence in connectionist music
  because of functional relationships
• Future work
• Generating other parts of songs (e.g. bass)
• Reducing the scaffold

27
Conclusion

• NEAT Drummer a new method for generating drum
  tracks for existing songs
• A new perspective on music generation functional
  relationships in scaffolding
• Generates a natural sound
• May lead to generating melodic tracks in the
  future

28
Special Thanks

• To Dr. Stanley who reviewed my slides and allowed
  me to use some of his images
• To Barry Taylor who allowed me to add NEAT
  Drummer rhythms to his MIDIs

29
Questions

• How does NEAT Drummer encode drum patterns?
• What is a CPPN?

30
References Pt.1

• Hoover, Amy K., Michael P. Rosario, and Kenneth
  O. Stanley. Scaffolding for Interactively
  Evolving Novel Drum Tracks for Existing Songs.
  Proceedings of the Sixth European Workshop on
  Evolutionary and Biologically Inspired Music,
  Sound, Art and Design (EvoMUSART 2008). New York,
  NY Springer, 2008
• McCormack, J. Open problems in evolutionary
  music and art. In Proc. of Applications of
  Evolutionary Comp., (EvoMUSART 2005). Volume 3449
  of Lecture Notes in Computer Science., Berlin,
  Germany, Springer Verlag (2005) 428436
• Takagi, H. Interactive evolutionary computation
  Fusion of the capacities of EC
• optimization and human evaluation. Proc. of the
  IEEE 89(9) (2001) 12751296
• Dawkins, R. The Blind Watchmaker. Longman,
  Essex, U.K. (1986)
• Todd, S., Latham, W. Evolutionary Art and
  Computers. Academic Press, London
• (1992)
• Nelson, G.L. Sonomorphs An application of
  genetic algorithms to growth and
• development of musical organisms. In 4th
  Biennial Art and Technology Symp.
• (1993) 155169

31
References Pt. 2

• Husbands, P., Copley, P., Eldridge, A., Mandelis,
  J. 1. In Evolutionary Computer
• Music. Springer London (2007)
• Biles, J.A. 2. In Evolutionary Computer Music.
  Springer London (2007)
• Todd, P.M., Loy, D.G. Music and Connectionism.
  MIT Press, Cambridge, MA (1991)
• Chen, C.C.J., Miikkulainen, R. Creating melodies
  with evolving recurrent neural
• networks. In Proc. of the 2001 Int. Joint Conf.
  on Neural Networks, Washington,
• D.C., IEEE Press (2001) 22412246
• Gomez, F., Miikkulainen, R. Solving
  non-Markovian control tasks with neuroevolution.
  (1999) 13561361
• Saravanan, N., Fogel, D.B. Evolving neural
  control systems. IEEE Expert (1995)2327
• Yao, X. Evolving articial neural networks.
  Proc. of the IEEE 87(9) (1999) 14231447
• Stanley, K.O., Miikkulainen, R. Evolving neural
  networks through augmenting topologies.
  Evolutionary Computation 10 (2002) 99127
• Stanley, K.O., Miikkulainen, R. Competitive
  coevolution through evolutionary
• complexication. 21 (2004) 63100
• Stanley, K.O. Compositional pattern producing
  networks A novel abstraction
• of development. Genetic Programming and
  Evolvable Machines Special Issue on
• Developmental Systems 8(2) (2007) 131162