Learning through creativity: how creativity can help machine learning achieving deeper understanding

  • Caterina Moruzzi
Keywords: creativity, artificial intelligence, autonomy, problem-solving, machine learning


In this paper, I address the difficult task of analysing the nature of creativity by suggesting a more objective way of defining it. In particular, I propose a minimal account of creativity as autonomous problem-solving process. This definition is aimed at providing a baseline that researchers working in different fields can agree on and that can then be refined on a case by case basis. Developing our insight on the nature of creativity is increasingly necessary in the light of recent developments in the field of Artificial Intelligence. In the second part of the paper, I discuss how an investigation on the main features of human creativity can support the advancement of machine learning models in their current areas of weakness, such as intuition, originality, innovation, and flexibility. I suggest how methods such as modelling the human brain or simulation can be useful to extract the main mechanisms underlying creative processes and to translate them to machine learning applications. This can eventually aid both the development of machine learning systems that achieve a deeper and more intuitive understanding and our exploration of human creativity.


Abdurahiman, Paul (1994), «Machine Learning and Simulation Model Specification» in Simulation Practice and Theory, vol. 2, pp. 1-15.

Albert, Robert, Runco, Mark (1999), The History of Creativity Research, in Sternberg, Robert (ed.) (1999), Handbook of Human Creativity, Cambridge University Press, New York.

Alpaydin, Ethem (2009), Introduction to Machine Learning, MIT Press, Cambridge (MA).

Ariza, Christopher (2009), «The Interrogator as Critic: The Turing Test and the Evaluation of Generative Music», in Computer Music Journal, vol. 33, pp. 48-70.

Boden, Margaret (1990), The Creative Mind: Myths and Mechanisms, George Weidenfeld and Nicolson, London.

Bown, Oliver (2011), «Experiments in Modular Design for the Creative Composition of Live Algorithms», in Computer Music Journal, vol. 35, pp. 73-85.

Bridy, Annemarie (2012), «Coding Creativity: Copyright and the Artificially Intelligent Author», in Stanford Technology Law Review, vol. 5, pp. 1-28.

Briot, Jean Paul, Hadjeres, Gaetan, Pachet, Francois (2017), «Deep Learning Techniques for Music Generation - A Survey», arXiv:1709.01620 [cs.SD].

Carter, Shan et al. (2019), «Activation Atlas», from https://distill.pub/2019/activation-atlas/.

Castellano, Federico (2018), «What can Philosophy Teach Machine Learning?», in Medium, 7/12/2018, from https://towardsdatascience.com/what-can-philosophy-teach-machine-learning-4ff091d43de6.

Chella, Antonio, Griffiths, Sascha, Wiggins, Geraint (eds.) (2016), «Robotics and Creativity», special issue in Robotics and Autonomous Systems, vol. 86.

Chella, Antonio, Manzotti, Riccardo (2012), «Jazz and Machine Consciousness: Towards a New Turing Test», proceedings of AUSB/IACAP 2012 Symposium.

Colin, Thomas et al. (2016), «Hierarchical Reinforcement Learning as Creative Problem Solving», in Robotics and Autonomous Systems, vol. 86, pp. 196-206.

Colton, Simon (2008), «Creativity Versus the Perception of Creativity in Computational Systems», in AAAI Spring Symposium: Creative Intelligent Systems.

Dartnall, Terry (ed.) (1994), «Artificial Intelligence and Creativity», in Studies in Cognitive Systems, vol. 17.

Dewey, John (1934), Art as Experience, Minton, Balch & Co, New York.

D’Inverno, Mark, McCormack, Jon (eds.) (2012), Computers and Creativity, Springer, London.

Dong, Hao-Wen et al. (2017), «MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment», arXiv:1709.06298.

Edmonds, Ernest (1994), «Introduction: Computer-based Systems that Support Creativity» in Dartnall (1994), pp. 327-334.

Elton, Matthew (1995), «Artificial Creativity: Enculturing Computers», in Leonardo, vol. 28, pp. 207–213.

Fabisch, Alexander et al. (2016), «A Survey of Behavior Learning Applications in Robotics: State of the Art and Perspectives», in arXiv:1906.01868.

Gaut, Berys (2010), «The Philosophy of Creativity», in Philosophy Compass, vol. 5, n. 12, pp. 1034-1046.

Goldman, Alvin I. (ed.) (1993), Readings in Philosophy and Cognitive Science, MIT Press, Cambridge (MA).

Halford, Graeme S., Levinson, Robert (1994), «Introduction: Creativity and Cognition» in Dartnall (1994), pp. 139-144.

Harney, Maurita (1994), «Clues to Creativity» in Dartnall (1994), pp. 195-208.

Jiang, Mingming, Thagard, Paul (2014), «Creative Cognition in Social Innovation», in Creativity Research Journal, vol. 26, n. 4, pp. 375-388.

Kralik, Jerald et al. (2016), «Modeling Incubation and Restructuring for Creative Problem Solving in Robots», in Robotics and Autonomous Systems, vol. 86, pp. 162-173.

Lake, Brenden et al. (2011), «One Shot Learning of Simple Visual Concepts», from https://cims.nyu.edu/~brenden/LakeEtAl2011CogSci.pdf.

Le, Nam (2019), «Evolving Self-taught Neural Networks: The Baldwin Effect and the Emergence of Intelligence», arXiv:1906.08854v1.

Lesort, Timothée et al. (2019), «Continual Learning for Robots», arXiv:1907.00182v1.

Levinson, Robert (1994), «Experience-based Creativity», in Dartnall (1994), pp. 161-179.

Luck, Michael, D’Inverno, Mark (2012), «Creativity Through Autonomy and Interaction» in Cognitive Computation, vol. 4, pp. 332-346.

Minsky, Marvin (1982), «Why People Think Computers Can't», in AI Magazine, vol. 3, n. 4, DOI: https://doi.org/10.1609/aimag.v3i4.376 .

Moruzzi, Caterina (2018), «Creative AI: Music Composition Programs as an Extension of the Composer’s Mind», in Müller, Vincent C. (ed.), Philosophy and Theory of Artificial Intelligence 2017, Springer, Berlin, DOI: 10.1007/978-3-319-96448-5_8.

Parker, Wendy S. (2008), «Computer Simulation», in Curd, Martin, Psillos, Stathis (eds.) The Routledge Companion to Philosophy of Science, Routledge, New York, pp. 135-145.

Paul, Elliot, Kaufman, Scott (eds.) (2014), The Philosophy of Creativity, Oxford University Press, Oxford.

Silva, Vivian et al. (2019), «On the Semantic Interpretability of Artificial Intelligence Models», https://arxiv.org/abs/1907.04105.

Silver, David et al. (2017), «Mastering the Game of Go Without Human Knowledge», in Nature, vol. 550, n. 7676, p. 354.

Simon, Herbert (1985), «What We Know About the Creative Process», in Kuhn, Robert (ed.), Frontiers in Creative and Innovative Management, Ballinger, Cambridge, pp. 3–22.

Stanciu, Marius (2015), «Embodied Creativity: A Critical Analysis of an Underdeveloped Subject», in Procedia - Social and Behavioral Sciences, vol. 187, pp. 312-317.

Still, Arthur, D’Inverno, Mark (2016), «A History Of Creativity For Future AI Research», in Pachet, F. et al. (eds.), Proceedings of the 7th International Conference on Computational Creativity, (ICCC), pp. 147-154.

Tavanei, Amirhossein et al. (2018), «Deep Learning in Spiking Neural Networks», arxiv:1804.08150.

Thagard, Paul (1990), «Philosophy and Machine Learning», in Canadian Journal of Philosophy, vol. 20, pp. 261-76.

Thagard, Paul (2006), Philosophy of Psychology and Cognitive Science, Elsevier, Amsterdam.

Thagard, Paul (2010), The Brain and the Meaning of Life, Princeton University Press, Princeton.

Thagard, Paul (2012), The Cognitive Science of Science: Explanation, Discovery, and Conceptual Change, MIT Press, Cambridge (MA).

Thagard, Paul, Stewart, Terrence (2011), «The AHA! Experience: Creativity Through Emergent Binding in Neural Networks», in Cognitive Science, vol. 35, pp. 1-33.

Van Der Schyff, Dylan et al. (2018), «Musical Creativity and The Embodied Mind: Exploring The Possibilities of 4E Cognition And Dynamical Systems Theory», in Music and Science, vol. 1, pp. 1-18.

Wallas, Graham (1926), Art of Thought, Harcourt-Brace, New York.

Wiggins, Geraint (2005), «Searching for Computational Creativity», in New Generation Computing, vol. 24, pp. 209-222.

Wiggins, Geraint (2006), «A Preliminary Framework for Description, Analysis and Comparison of Creative Systems», in Knowledge-Based Systems, vol. 19, pp. 449-458.

Wiggins, Geraint, Pearce, Marcus, Müllensiefen, Daniel (2011), «Computational Modelling of Music Cognition and Musical Creativity», in The Oxford Handbook of Computer Music, Oxford University Press, Oxford.

Wu, Felix et al. (2019), «Simplifying Graph Convolutional Networks», arXiv:1902.07153.

How to Cite
Moruzzi, C. (2020) “Learning through creativity: how creativity can help machine learning achieving deeper understanding”, Rivista Italiana di Filosofia del Linguaggio, 14(2). doi: 10.4396/AISB201904.