Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

S3 tutorial - Creativity

69 views

Published on

Creative Evolutionary
Algorithms:
Evolutionary Art & Music

Published in: Technology
  • Be the first to comment

  • Be the first to like this

S3 tutorial - Creativity

  1. 1. Creative Evolutionary Algorithms: Evolutionary Art & Music Francisco Fernández de Vega University of Extremadura, Spain fcofdez@unex.es
  2. 2. “...Although the ultimate goal may be the creation of artif icial intelligence that is capable of producing high quality works of art without human intervention (...) Personally I’d rather man stay ahead and in control of the very aspects of life that make it worth living, and rely on machines to help us with those things that they are currently best at, relieving us of the mundane and tedious, rather than taking over our most enjoyable pastimes and leaving creativity to man and God!” M. Mumford, Fellow of the Royal British Photographic Society. Excerpt from XY foreword, Parlamento de Extremadura, 2014. ISBN 978-84-96757-50-9.
  3. 3. Summary ● Introduction: Creativity & EAs. ● Art & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  4. 4. Summary ● Introduction: Creativity & Eas. ● Art & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  5. 5. ● Main goal for an Evolutionary Algorithm: – Finding the best (or good enough) solution. Creativity and EAs
  6. 6. ● Quality assessment in an EA: – Every candidate solution must be evaluated. Creativity and EAs
  7. 7. ● Quality assessment in an EA: – Every candidate solution must be evaluated.. – A final evaluation is required to accept/reject the output of the run. Creativity and EAs
  8. 8. Creativity and EAs ● EAs can be creative when providing solutions.
  9. 9. Creativity and EAs ● What is creativity? Wikipedia: Creativity is a phenomenon whereby something new and valuable is created. It has to do with novelty and originality... but that's not enough: random processes typically produce uninteresting results.
  10. 10. Creativity and EAs ● Novelty search? (K. Stanely) – Does not reward progress. – Rewards being different. Novel? Addition of an anti-freeze fish gene to strawberries give it this blue hue
  11. 11. Creativity and EAs ● Being different: Diversity is useful. ● Evolution needs diversity (check diversity in EAs). Ursem, R. K. (2002, September). Diversity-guided evolutionary algorithms. In International Conference on Parallel Problem Solving from Nature (pp. 462-471). Springer, Berlin, Heidelberg. Alfaro-Cid, E., Merelo, J. J., Fernandez de Vega, F., Esparcia-Alcázar, A. I., & Sharman, K. (2010). Bloat control operators and diversity in genetic programming: A comparative study. Evolutionary Computation, 18(2), 305-332.
  12. 12. Creativity and EAs ● Computational Creativity? – A subfield of AI with some goals: ● To provide computational perspective of human creativity, in order to help us to understand it. ● To enable machines to be creative. ● To produce tools which enhance human creativity. (On impact and evaluation in Computational Creativity: A discussion of the Turing Test and an alternative proposal, A. Pease & S. Colton)
  13. 13. Summary ● Introduction: Creativity and EAs. ● Arts & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  14. 14. Summary ● Introduction: Creativity and EAs. ● Arts & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  15. 15. Generative Art and Computers ● Cybernetic Serendipity Exhibition, London, 1968. http://cyberneticserendipity.net /
  16. 16. How to put creativity within computers ● AARON: Probably the first robot artist. ● Expert system writen in LISP.
  17. 17. The Painting Fool ● About me: I'm The Painting Fool: a computer program, and an aspiring painter. http://www.thepaintingfool.com
  18. 18. Art and Computers ● Two main questions: – How can we encode the main ingredients for creativity within an algorithm? – How can we measure aesthetic quality? The persistence of Memory, S. Dalí.
  19. 19. Art and Computers Where do artists find their inspiration? Gaudi
  20. 20. Art and Computers ● Two main problems to address: – Motivational force (& inspiration). – Measuring/being aware of aesthetic quality.
  21. 21. Art and Computers ● My motivational force...
  22. 22. Art and Computers ● Motivational force & inspiration: – Cultural tradition. – Tangible forms for spiritual concepts. – Recording history. – Visual language to convey teachings. – Tell a story. – Reflecting beauty of nature. – Express the ideal or expose the real. – Provoke others to think. – Experimenting with formal elements and quality of medium.
  23. 23. Art and Computers ● Measuring aesthetic quality: – Many proposals, such as: ● Birkhoff and the Aesthetic Measure ● The Golden Ratio ● Zipf’s Law ● Fractal Dimension ● Gestalt Principles ● The Rule of Thirds – … but, do they guarantee the quality of the result?
  24. 24. ● Useful in both steps of evaluation?: – Fitness evaluation step within the EA loop. – Final evaluation is required to accept/reject the output of the run. Art and Computers
  25. 25. Art & Computers A Turing Test for Creativity? Colton, S. (2008). Creativity Versus the Perception of Creativity in Computational Systems. In AAAI Spring Symposium: Creative Intelligent Systems (pp. 14-20).
  26. 26. Creativity and EAs ● Is it enough Turing Test to asses the artistic value of a work? ● What happens with human art that seems computer generated art? – Check for instance Schoenberg serialism and antonality.
  27. 27. Creativity and EAs ● Some authors consider that creativity must only be assessed by means of the output (second stage of evaluation): – “For the purposes of setting up an initial framework, we shall adopt the assumption that the internal workings of a program are not part of the relevant data”. Ritchie, G. 2007. Some empirical criteria for attributing creativity to a computer program. Minds and Machines 17:67–99.
  28. 28. Art and Computers ● Measuring aesthetic quality...is not easy Cezanne Monet Van Gogh
  29. 29. Art and Computers ● Introduction. ● Art & Computers. ● Evolutionary Art. ● Unpplugged Evolutionary Algorithms. ● Evolving music.
  30. 30. Art and Computers ● Introduction. ● Art & Computers. ● Evolutionary Art. ● Unpplugged Evolutionary Algorithms. ● Evolving music.
  31. 31. Evolutionary Art ● A hot topic in computer science...
  32. 32. Interactive Evolutionary Algorithms ● Standard EA: – Fitness Evaluation. – Selection. – Crossover+Mutation. ● Interactive EA: – Fitness Evaluation (human made). – Selection. – Crossover+Mutation.
  33. 33. Evolutionary Art ● W. Latham, Formsynth, 1984.
  34. 34. Interactive EAs ● IEA: An evolutionary Algorithm with a human being in charge of fitness evaluation.
  35. 35. Evolutionary Art ● Collaborative works...: – Picbreeder (Secretan et al). – EvoEco (Kowaliw, Dorin, McCormack). EvoEco.
  36. 36. Evolutionary Art ● Evolutionar Art applications = Evolutionary Design: – Endless forms (Clune & Lipson).
  37. 37. Evolutionary Design: Genetic Terrain Programming ● Genetic Terrain Programming: – Interactive GP.
  38. 38. Evolutionary Design ● Some of the terminals:
  39. 39. Previous Work
  40. 40. Previous work ● Genetic Terrain Programming.
  41. 41. Generative Art and Computers ● GTP technology applied in videogames.
  42. 42. Evolutionary Art ● Open problems in Evolutionary Art (McCormak): – Useful genotypes and phenotypes. – Fitness Functions embodying human aesthetic evaluation. – Evolutionary Art complying standards for evolutionary art. – Ecosystems that recognize their own creativity. – Developing Evolutionary Art theories. McCormack, J. (2005). Open problems in evolutionary music and art. In Applications of Evolutionary Computing (pp. 428-436). Springer Berlin Heidelberg.
  43. 43. Our Goal ● More closely working with artist. ● Involving them in evolutionary art experiments. ● Learning from them to better understand creativity from the EA Point of view. ● Providing technology that helps.
  44. 44. Our Goal ● How to reach our goal: – Technology: Developing an easy to use software tool (EVOSPACE). – Developing a new methodology: Unplugged EAs.
  45. 45. Summary ● Introduction. ● Art & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  46. 46. Summary ● Introduction. ● Art & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  47. 47. Unplugging EAs ● Standard EA. – Fitness Evaluation. – Selection. – Crossover + Mutation. ● Interactive EA. – Fitness Evaluation. – Selection. – Crossover + Mutation.
  48. 48. Unplugging EAs ● Quality assessment in an EA: – Every candidate solution must be evaluated (Interactive EAs). – A final evaluation is required to accept/reject the output of the run (?).
  49. 49. Unplugging EAs ● Interactive EA. – Fitness Evaluation. – Selection. – Crossover + Mutation. ● Unplugged EA. – Fitness Evaluation. – Selection. – Crossover + Mutation.
  50. 50. Unplugging EAs ● Our Team: – 5 artists. – 1 coordinator. ● Way of working: – #1 Artists decide the initial population. – #2 Working isolated, they evaluate, select parents, and apply crossover + mutation creating a new individual. – #3 Individuals sent to the coordinator by email. – #4 The coordinator anonymously share them in a dropbox folder.
  51. 51. Unplugging EAs ● The first experiment: – 10 weeks: October 2012 - January 2013. – 5 artists x 10 weeks (1 work per week)= 50 paintings.
  52. 52. Unplugging EAs ● First step: Seeding the initial population: – Choosing a well-known painting... Question #1: Which painting would you have selected for the initial population?
  53. 53. Unplugging EAs ● What did artists selected for the initial population? Botticelli, Birth of Venus; Schiele, Sitting Woman with Legs Drawn Up; Millais, Ophelia; Schiele, Seated Man; Leonardo Da Vinci, The last supper.
  54. 54. Unplugging EAs ● Second Step (every week). – Artists select two parents. – Decide mutation and crossover to apply. – Generate a new painting.
  55. 55. Unplugging EAs ● Question #2: Can you figure out the parents for any of the paintings?
  56. 56. Unplugging EAs
  57. 57. Unplugging EAs ● #3 Individuals sent to the coordinator, ● #4 anonymously shared in a dropbox folder... and going back to step #1
  58. 58. Unplugged EAs ● Three first generations.
  59. 59. Unplugging EAs Comparing initial and latest generations.
  60. 60. Unplugging EAs ● What kind of mutation and crossover operations have been applied?
  61. 61. Unplugging EAs G7-5 by L. Navarro
  62. 62. Unplugging EAs - Self-reflection process: it tries to not only reason about the work to be produced, but also on how the evolutionary process is working -converging- and the best way to influence and change the behavior of the algorithm itself so that more diversity is added.
  63. 63. Unplugging Eas. G9-3: By C. Cruz
  64. 64. Unplugging EAs ● Artists feel a need to to use and manipulate natural media. ● The diversity observed is much grater than that generated with available IEAs. ● This observation, expressed by the audience, is aligned with some of the problems described by McCormack when referring to evolutionary art: “there is still a large distance between evolutionary art and the art that human artists can produce.” McCormack, J.: Open problems in evolutionary music and art. In: EvoWorkshops, pp. 428{436 (2005)
  65. 65. Unplugging EAs ● Quality assessment in an EA: – Every candidate solution must be evaluated (IEA). – A final evaluation is required to accept/reject the output of the run.
  66. 66. Unplugging EAs ● Final Evaluation: Involving other actors in the EA world: – Audience. – Galleries. – Museums. – Art Critics.
  67. 67. Unplugging EAs ● Analyzing audience response is part of the creativity assessment: – Survey based approach. – Non-intrusive methods (kinnect based approach).
  68. 68. Unplugging EAs ● Analyzing audience response – main conclusions: – Survey produce fatigue – better use non-intrusive methods: ● Amount of data collected grows. ● Information collected is coherent with surveys. ● Data can be compared with artists creativity displayed. Analyzing Evolutionary Art Audience Interaction by Means of a Kinect Based Non-intrusive Method. F. Fernánez de Vega, M. García, JJ. Merelo, G. Aguilar, C. Cruz, P. Hernández. To appear in Volume 785 of the Studies in Computational Intelligence series.
  69. 69. Unplugging EAs ● Final Evaluation: Involving other actors in the EA world: – Audience. – Galleries. – Museums. – Art Critics.
  70. 70. Galleries & Museums ● Art exhibits in three different galleries worldwide. Back Gallery Project – Vancouver Gallery Louchard – Paris MC Gallery – Manhattan - NY
  71. 71. International Competitions ● Best way to evaluate the results of an Evolutionary Art project. ● Submitted our work to: – ACM GECCO Evolutionary Art, Design and creativity competition 2013 winner. – 2017 re:artiste Show Your World International Art Competition and juried exhibition.
  72. 72. International Competitions ● XY: Winner ACM Gecco 2013 Evolutionary Art Design and Creativity competition. ● Finalist 2017 re:artiste show your world competition.
  73. 73. Summary ● Introduction. ● Art & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  74. 74. Summary ● Introduction. ● Art & Computers. ● Evolutionary Art. ● Unplugged Evolutionary Algorithms. ● Evolving music.
  75. 75. Music is a nice gameboard for EAs ● Many problems available. ● Just a sample: – 4-part harmonization problem.
  76. 76. 4-part problem Harmonization Chromosome includes: chord progression + SATB voices. Two stages Genetic Algorithm evolves first the progression and then the voices.
  77. 77. 4-part problem Harmonization
  78. 78. Another music problem: automatic transcription ● Automatic transcription of piano music by means of Genetic Algorithms.
  79. 79. Automatic transcription ● Remember, evaluate in the appropriate context, and add a final evaluation step: – ISMIR 2011, MIREX Competion: 3rd position in piano transcription. Gustavo Reis, Francisco Fernández de Vega, Aníbal Ferreira:
 Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level Estimation. IEEE Trans. Audio, Speech & Language Processing 20(8): 2313- 2328 (2012)
  80. 80. Automatic transcription ● Remember, evaluate in the appropriate context, and add final evaluation step : – ISMIR 2011, MIREX Competion: 3rd position in piano transcription. Gustavo Reis, Francisco Fernández de Vega, Aníbal Ferreira:
 Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level Estimation. IEEE Trans. Audio, Speech & Language Processing 20(8): 2313- 2328 (2012)
  81. 81. Summary ● Try to add diversity, novelty and creativity to your algorithm. ● Evaluate it in the appropriate context. ● If dealing with art and music add an extra evaluation step for the final result.
  82. 82. Residence for European Researchers. Available for researchers collaborating with our group (free of charge).
  83. 83. Thank you. Find me at GP bibliography: http://www.cs.bham.ac.uk/~wbl/biblio/gp- html/FranciscoFernandezdeVega.html fcofdez@unex.es

×