MPŠ
MPŠ MP&Scaron MP&Scaron MP&Scaron Avtorji

Jožef Stefan
International
Postgraduate School

Jamova 39
SI-1000 Ljubljana
Slovenia

Phone: +386 1 477 31 00
Fax: +386 1 477 31 10
Email: info@mps.si

Search

Course Description

Computational Creativity

Program

Information and Communication Technologies, third-level study programme

Lecturers:

doc. dr. Martin Žnidaršič
dr. Senja Pollak
prof. dr. Nada Lavrač

Goals:

The goal of the course is introduction into the field of computational creativity, its theory, as well as its practical aspects: tools, technologies and applications.

Students learn the methodology for evaluation of the methods and results of computational creativity, recognize the limitations of computational creativity and know how to identify problems in which it is applicable.

Key general methods in this research area are conceptual blending and bisociative discovery of new concepts. In addition to these, selected methods and techniques are presented that are used in specific use cases: natural language processing and language resources, data mining, data representation, use and production of semantic networks.

Course aims to provide knowledge that is necessary for the independent development of new methods and applications of computational creativity in real world problems.

Content:

Introduction:
introduction to the field of computational
creativity, positioning of the field and
sample applications

Foundations:
definitions of human and computational
creativity, evaluation and metrics

Methodology:
computational creativity as search, bisociative
knowledge discovery, concept formation and
conceptual blending

Resources and tools:
language resources and tools for natural
langugage processing (corpora, programing
libraries, lexical and semantic resources),
structured and textual data mining,
supporting platforms for computational
creativity (Clowdflows, TextFlows, Flowr,
Pattern)

Applications in science, health and marketing:
hypothesis creation, knowledge discovery,
proving mathematical axioms, food recipe
creation, exercise planning, generation of
slogans, acronyms and advertisements

Applications in literature and art:
creation of stories, metaphor, humor, poetry
and paintings, composing music

Summary and discussion:
comparison of human and computational
creativity, opportunities, limitations and
ethical issues, the role of computational
creativity in industry and art

Course literature:

• M. A. Boden, Ed. Dimensions of creativity. MIT Press,1996.ISBN 0-262-02368-7
• M. A. Boden, The creative mind: Myths and mechanisms. Psychology Press, 2004. ISBN 0-203-50852-1
• T. R. Besold, M. Schorlemmer, and A. Smaill, Computational Creativity Research: Towards Creative Machines. Atlantis Publishing Corporation, 2014. ISBN 978-94-6239-084-3
• S. Colton, and G. A. Wiggins, Computational Creativity: The Final Frontier? In ECAI 2012 - 20th European Conference on Artificial Intelligence, 21-26, Montpellier, France, August 2012.
• G. A. Wiggins, A preliminary framework for description, analysis and comparison of creative systems. Knowledge-Based Systems 19 (7): 449–458, 2006.
• G. Ritchie, Some Empirical Criteria for Attributing Creativity to a Computer Program. Minds and Machines, 17(1):76-99, Springer, 2007.
• G. Fauconnier, and M. Turner, The way we think: Conceptual blending and the mind's hidden complexities. Basic Books, 2008. ISBN 0-465-08785-X
• M. R. Berthold, Bisociative knowledge discovery. Springer Berlin Heidelberg, 2011. ISBN 978-3-642-24799-6
• K.E. Jennings, Developing creativity: Artificial barriers in artificial intelligence. Minds and Machines 20(4): 489-501, 2011.

Significant publications and references:

• P. Tomašič, M. Žnidaršič, G. Papa, Implementation of a slogan generator In: The Fifth International Conference on Computational Creativity, 2014.
• M. T. Llano, R. Hepworth, S. Colton, J. Gow, J. Charnley, N. Lavrač, M. Žnidaršič, M. Perovšek, M. Granroth-Wilding, and S. Clark, Baseline Methods for Automated Fictional Ideation In Proceedings of the International Conference on Computational Creativity. 2014.
• J. Smailović, M. Grčar, N. Lavrač, and M. Žnidaršič, Stream-based active learning for sentiment analysis in the financial domain, Information Sciences 285: 181-203, 2014.
• M. Žnidaršič, S. Pollak, D. Miljković, J. Kranjc, N. Lavrač, Identifying creative fictional ideas In: Discovery science : book of abstracts, 2014.
• P. Tomašič, G. Papa, M. Žnidaršič, Automated slogan production using a genetic algorithm. In: Bioinspired optimization methods and their applications : proceedings of the Student Workshop on Bioinspired Optimization Methods and their Applications - BIOMA 2014, 13 September 2014, Ljubljana, Slovenia. Ljubljana: Jožef Stefan Institute, pp. 55-66, 2014.

Examination:

Seminar work (70%)
Written or oral exam (30%)

Students obligations:

Seminar and exam

Links: