Computational Creativity

Computational Creativity

• 1.
  International Journal ofTrend in Scientific Research and Development (IJTSRD) Volume 3 Issue 6, October 2019 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470 @ IJTSRD | Unique Paper ID – IJTSRD28094 | Volume – 3 | Issue – 6 | September - October 2019 Page 455 Computational Creativity Matthew N. O. Sadiku1, Nana K. Ampah2, Sarhan M. Musa1 1Roy G. Perry College of Engineering, Prairie View A&M University, Prairie View, Texas 2Lone Star College Kingwood, Houston, Texas ABSTRACT Computational creativity is a newly emerging field within AI that focuses on the capacity of machines to both generate and evaluate novel outputs that would be considered creative. It is the philosophy, science, and engineeringof computational systems which exhibit behaviors that unbiased observers would regard as creative. It is mainly concerned with building creative systems. It addresses processes that would be deemed creative if performed by a human. This paper provides an introduction to computational creativity. KEYWORDS: computational creativity, artificialcreativity, mechanicalcreativity, creative computing, creative computation How to cite this paper: Matthew N. O. Sadiku | Nana K. Ampah | Sarhan M. Musa "Computational Creativity" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456- 6470, Volume-3 | Issue-6, October 2019, pp.455-457, URL: https://www.ijtsrd.com/papers/ijtsrd28 094.pdf Copyright © 2019 by author(s) and International Journal ofTrendinScientific Research and Development Journal. This is an Open Access article distributed under the terms of the Creative CommonsAttribution License (CC BY 4.0) (http://creativecommons.org/licenses/by /4.0) INTRODUCTION The recent years have witnessed advancements in systems that facilitate human or autonomous creation. New technologies, such as artificial intelligence (AI), are drastically changing the creative processes. Instead of just viewing computer as a creativecollaboratorassistinghuman creators, we can see it as a creative entity in its own right. In view of the limitation of human creativity resources, it is imperative to develop technologies for greater creativity. Such creative systems can be used for autonomous creative tasks, such as inventing mathematical theories, writing poems, painting pictures, and composing music. Innovation is becoming accepted as central to competitiveness intoday’s world.Creativityisa fundamental ingredient for the completion of engineering design tasks. It is manifested in many ways, such as invention of new concepts and ideas or production of objects of artandmusic. Three different types of creativity have been identified: (1) Exploratory creativity, (2) Transformational creativity, (3) Combinational creativity. CONCEPT OF COMPUTATIONAL CREATIVITY Computational creativity (CC) (also known as artificial creativity or creative computation) is an emerging branch of artificial intelligence (AI) thatplacescomputers atthecenter of the creative process. It involves a generative step to produce many ideas and a selective step to determine the ones that are the best [1]. It is the generation of a product that is judged to be novel. Interaction between human and machine is based on the human cognitive process of creativity, as shown in Figure 1[2]. Figure1. Stages in the cognitive process of creativity [2]. As shown typically in Figure 2 [3], CC is a multidisciplinary area that embraces several fields of artificial intelligence, computer science, mathematics, literature, architecture, engineering , cognitive science, philosophy,andthearts. The goal of computational creativity is to model, simulate or replicate creativity using a computer [4]. IJTSRD28094
• 2.
  International Journal ofTrend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470 @ IJTSRD | Unique Paper ID – IJTSRD28094 | Volume – 3 | Issue – 6 | September - October 2019 Page 456 Figure2. Computational Creativity as a multidisciplinary field [3] Computational creativity should be explored from four different perspectives, known as the four Ps: Person, Product, Process and Press [5,6]: Person: The individual agent or producerthatisseenas creative. The Person approachismeanttodiscoverwhat personality, emotional, and cognitivetraitsdistinguisha more creative person from a less creative one. Process: What the creative individual does to be creative. The Process perspective includesanytheoryof how creative products are made. Product: What is produced as a result of the creative process. Generating creative products is an index of significant success for computational creativity.Inother words, many evaluations in computational creativity focus on Product perspective, which is useful for systems that have the goal of producing something useful to humans. Press: The environment in which the creativity is situated. It is the surrounding culture which influences people, processes, andproductsandwhichdeterminesif they creative or uncreative. The Press perspective focuses on what kind of social effect a product needs to have to be called creative. These four perspectives are illustrated in Figure 3[7]. Figure3. How the four Ps fit together in creativity [5] New technologies, such as machinelearningandbigdata, are drastically changing the nature of CC. Learning is an important part of creativity. Human learning involves many behaviors, including memorization, comprehension, and generalization. It is expedient to look at how machine learning developed to suggest future directions for computational creativity research. Computational creativity techniques that use machine learning (ML) train and learn can be used to approximate the examples. ML has shown promise for many creative tasks such as music generation, image and painting generation, image style transfer, etc. APPLICATIONS The goal of computational creativity is to build systems that do things that are creative. CC has been developed for applications ranging from music to mathematics. Some computational creative machines include IBM’s Watson and Deep Blue. Watson is a computational creativity machine that creates new stuff from its knowledge of existing stuff. Besides these, creative machines cover subjects like humor, poetry, games, music, design, code generation, and visual arts. Music: Computational creativity in the music domain has focused both on the generation of music for human musicians and generation of music for performance by computers. There is a large number dealing with the problem of automatic harmonization using several AI techniques. The harmonization problem is approached using a combination of neural networks and case-based reasoning. A robot can be used to create and play a multitude of orchestrated melodies. Visual Arts: Today, artists are extensively using technology to enhance their artistic expressions. Most work on visual creativity is conceptualized in terms of painting or drawing. Computational creativity in generating visual art has had some notable successes in the creation of representational art. The painterAARON is a robotic system that was developed by the artist and programmer Harold Cohen. Visual art AARON can pick up a paintbrush with its robotic arm, paint on canvas, and draw people. Computer Games: Games constitute the killer application for computational creativity.Theintegrating computational creativity philosophies and techniques into the game design process is a natural nextstepinthe computational intelligence and games evolution. A newly emerging area of computational creativity is that of video games [8]. Chess has been a traditional challenge for AI. With the defeat of then-world chess champion Garry Kasparov to IBM’s Deep Blue supercomputer in 1997, there is littlecontroversyabout the fact that the best programs outperform the best human players. CC Exercises: Promoting computational thinking is a priority in STEM and non-STEM disciplines. The goal of the Computational Creativity Exercises (CCEs) istohelp students better learn course material and be able to apply their new knowledge and skills to complex, real- world problem-solving situations. Through computational creativity, students canleveragecreative thinking skills to “unlock” their understanding of computational thinking. CCEs improve student learning and achievement [9]. Other areas of application of CC include robotics, education, information fusion systems, and culinary recipe. BENEFITS AND CHALLENGES Computational creativity research crosses several disciplinary boundaries across the arts, sciences, and
• 3.
  International Journal ofTrend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470 @ IJTSRD | Unique Paper ID – IJTSRD28094 | Volume – 3 | Issue – 6 | September - October 2019 Page 457 engineering. It showcases ways of producing unpredictable behavior that goes beyond explicit program instructions, such as connectionist computation, evolutionarycomputing, emergence or the use of randomness [10]. A computational creativity system can test quadrillions of ideas at once without needing to invoke modularity as humans do. Building creative software offers both a technical challenge and a social one. Creativity is very difficultandhardtodefine in objective terms. It seems mysterious to a lot of people. Even within computer science community, some are still skeptical about the creative potential ofsoftware.Detractors of computational creativity argue that it is impossible to simulate creative human thinking and reasoning in view of the fact that computers cannot be creative beyond what the programmer provides the system. Others holdthepervasive belief that to be creative requires having a special gift bestowed by a higher power. Creativity can be negative and it is not as always good. For example, an employee devices an effective way to steal from the employer [11]. Human creativity has been a compelling but elusive concept to study and formalize. Creativityisdifficulttostudybecause of its connections with poorly understood phenomena such as intuition, insight, genius studies, and brain processes. Evaluation of creative systems is a challenging problem in computational creativity. CONCLUSION Computational creativity is an emerging subfield of AI that places computers in the heart of the creative process. As a field of research, CC is a growing and thriving, and creative systems have been developed for many applications. As CC continues to grow in popularity, it is increasingly being taught in some form as a university-level course [12]. More information about CC can be found in the books in[13- 15] and three specialized journals: Creativity Research Journal, Journal of Creative Behavior, and International Journal of Design CreativityandInnovation. TheInternational Conference on Computational Creativity (ICCC) series, organized by the Association for Computational Creativity (http://computationalcreativity.net/home/) since 2010, is the only scientific conference that focuses on computational creativity alone [16]. REFERENCES [1] L. R. Varshney et al., “A big data approach to computational creativity: The curious case of Chef Watson,” Ref = a paper or online [2] F. Pinel and L. R. Varshney, “Computational creativity for culinary recipe,” Proceedings of CHI, Toronto, Canada, April/May 2014, pp. 439-442. [3] M. Navarro and J. M. Corchado, “Machine Learning in Music5Generation,” Oriental Journal of Computer Science and Technology, vol. 11, no. 2, 2018, pp. 75-77. [4] “Computational creativity,” Wikipedia, the free encyclopedia https://en.wikipedia.org/wiki/Computational_creativit y [5] A. Jordanous, “Four PPPPerspectivesoncomputational creativity in theory and in practice,” Connection Science, vol.28, no.2, 2016, 194–216. [6] H. Toivonen and O. Gross, “Data mining and machine learning in computational creativity,” Wiley Interdisciplinary Reviews, vol. 5, no. 6, November/December 2015, pp. 265-275. [7] C. Lamb, D.. Brown, and C.. A. Clarke, “Evaluating computational creativity:An interdisciplinarytutorial,” ACM Computing Surveys, vol. 51, no. 2, February 2018. [8] D. Ventura, “Beyond computational intelligence to computational creativityingames,”ProceedingsofIEEE Conference on Computational Intelligence and Games , Sept. 2016. [9] M. S. Peteranetz et al., “Helping engineering students learn in introductory computer science (CS1) using computational creativity exercises (CCEs),” IEEE Transactions on Education, vol. 61, no. 3, August 2018, pp. 195-203. [10] A. K. Jordanous,“Evaluatingcomputational creativity:A standardised procedure for evaluating creative systems and its application,” Doctoral Dissertation, University of Sussex, December 2012. [11] M. M. al-Rifaiea et al., “On evil and computational creativity,” Connection Science, vol.28,no.2,2016,171– 193. [12] M. Ackerman et al., “Teaching Computational Creativity” Proceedings of the 8th International Conference on Computational Creativity, Atlanta, June 2017. [13] T. R. Besold, M. Schorlemmer, and A. Smaill, Computational Creativity Research: Towards Creative Machines. Atlantis Press, 2015. [14] M. Filimowicz and V. Tzankova (eds.), Teaching Computational Creativity. Cambridge, 2017. [15] A. Iqbal et al.,The Digital Synaptic Neural Substrate: A New Approach to Computational Creativity. Springer, 2016. [16] A. Pease and A. Jordanous, “Report on the eighth international conference on computational creativity,” AI Magazine, vol 39, no 1, Spring 2018, pp. 62-64.