Computational Creativity Research Articles

Computational creativity beyond machine learning.

Computational creativity beyond machine learning.

자동창작시대의 예술 작품 -인공지능은 예술 창작의 주체가 될 수 있는가?

Computational creativity is emerging as a sub-field of computer science; it attempts to make machines the subjects of artistic creations. Therefore, we examine whether machines can be considered the subjects of artistic creations through experiments on audiences’ appreciation of works by artificial intelligence (AI) and humans. According to our qualitative and quantitative findings, audiences reported no significant differences in appreciating works by AI and humans. Thus, it seems inappropriate to declare that “AI cannot be the subject of an artistic creation.” Prior to asking, “Can machines create art?” it is necessary to ask “Isn’t a human a kind of machine?” It is contradictory if we deny that humans are machines, because they are also formed by evolution, a mechanical algorithm. If humans are a type of machine, and if they also make art, eventually, this will come to mean that machines create art. In conclusion, it is not natural to deny the hypothesis, “Machines can be the subjects of artistic creations.”

Examining Board Gameplay and Learning: A Multidisciplinary Review of Recent Research

Background Recent years have seen the resurgence of board games designed for entertainment, and to teach or explicate real life problems. The revival of board gameplay has been discussed in mainstream media, and has drawn the attention of researchers. Yet, in the field of games studies, the conception of games as learning spaces is mostly emphasized through digital/video games. Aim This literature review reveals the current knowledge regarding the learning potential of board games in various settings, subjects, and diverse learners. Results Board games are spaces for mathematical learning and learning spaces that can enable the learning of various contents. Board games allow for various interactions that result in players engaging in computational thinking, teamwork, and creativity. Conclusion The relationship between board gameplay and learning is evidenced across disciplines and countries. Board games simplify complex issues and systems, which make them appropriate to further explore learning and concepts such as motivation and computational thinking in formal and informal settings. Furthermore, there is need to expand research on learning in commercial board games.

Creativity and Multimodality

Creativity studies have been expanding into multimodality in recent years, particularly in the field of computational creativity (Elgammal and Saleh, 2015) and cognitive science (Gardner, 2008). Comparatively, linguistics is far behind in productivity in this area. A key linguistic contribution by Carter (2004) theorizes creativity in everyday common talk into two main categories: pattern-reforming and patternforming. This paper extends Carter’s (2004) hypothesis on linguistic creativity to multimodal texts. Inspired by the concept of ‘given’ and ‘new’ from Halliday’s (1967) information status, a new framework for creativity analysis is proposed and discussed in detail using scenes from TV drama House M.D., movie Casablanca (1942), sitcom Blackadder the Third (1987), digital arts such as logos of the Hong Kong Polytechnic University, Tesla Inc., Hotel ICON, fractal art from the novel Jurassic Park (1990) as well as viral MTV of Pen-Pineapple-Apple-Pen – PPAP Song (2016). This paper also discusses the importance of a base unit of creativity to both the creator and the target. Special attention is placed on endo-referenced and exoreferenced creativity, and their relationship with the implicitness and explicitness of the formula of creativity construction.

Computational Creativity and Music Generation Systems: An Introduction to the State of the Art.

Computational Creativity is a multidisciplinary field that tries to obtain creative behaviors from computers. One of its most prolific subfields is that of Music Generation (also called Algorithmic Composition or Musical Metacreation), that uses computational means to compose music. Due to the multidisciplinary nature of this research field, it is sometimes hard to define precise goals and to keep track of what problems can be considered solved by state-of-the-art systems and what instead needs further developments. With this survey, we try to give a complete introduction to those who wish to explore Computational Creativity and Music Generation. To do so, we first give a picture of the research on the definition and the evaluation of creativity, both human and computational, needed to understand how computational means can be used to obtain creative behaviors and its importance within Artificial Intelligence studies. We then review the state of the art of Music Generation Systems, by citing examples for all the main approaches to music generation, and by listing the open challenges that were identified by previous reviews on the subject. For each of these challenges, we cite works that have proposed solutions, describing what still needs to be done and some possible directions for further research.

MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space

As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity. Related literature researches show that different factors, such as life experience, historical background, etc., would influence composition styles of poets, which considerably contributes to the high diversity of human-authored poetry. Inspired by this, we propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity. Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training. In this way, the model learns a controllable latent variable to capture and mix generalized factor-related properties. Different factor mixtures lead to diverse styles and hence further differentiate generated poems from each other. Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models.

Doilies Digitais: Um Estudo da Aplicação de Criatividade Computacional ao Crochê

Neste artigo descrevemos o que são os doilies e apresentamos algumas das ferramentas digitais de criação de padrões gráficos para o crochê. Constatamos que as ferramentas digitais, disponíveis durante o desenvolvimento deste trabalho, não incorporam efetiva criatividade computacional. Isto posto, esse artigo então apresenta a aplicação de lógicas computacional ao desenvolvimento do padrão para doilies de crochê e argumenta iminentes possibilidades de incorporação de criatividade computacional para a geração destes. A incorporação desses sistemas criativos dá se pela gradual atribuição de autonomia aos processos computacionais envolvidos e a relação que o artesão estabelece com estes, o resultado dessa interação influencia diretamente a emergência desses padrões. As relações entre o artesão e os sistemas criativos manifestam-se em um ecossistema de produção, e este artigo finaliza discutindo as potencialidades da incorporação de criatividade computacional para o design de doilies.

From Artificial to Extended Intelligence in Music Composition

This article explores the relationship and disparities between human and computational creativity by addressing the following questions: How well are computational creativity systems currently performing at creative tasks? Could computers outperform human composers? And, if not, is computational creativity a utopia? Automatic composition systems are examined with respect to Boden’s three criteria of creativity (novelty, surprise and value), as well as their assumptions about the nature of creativity. As an alternative to a competitive relationship between human and computational creativity, the article proposes the concept of a distributed human–computer co-creativity, in which computational creativity extends – rather than replaces – human creativity, by expanding the space of creative possibilities.

Human Creativity and Consciousness: Unintended Consequences of the Brain's Extraordinary Energy Efficiency?

It is proposed that both human creativity and human consciousness are (unintended) consequences of the human brain’s extraordinary energy efficiency. The topics of creativity and consciousness are treated separately, though have a common sub-structure. It is argued that creativity arises from a synergy between two cognitive modes of the human brain (which broadly coincide with Kahneman’s Systems 1 and 2). In the first, available energy is spread across a relatively large network of neurons, many of which are small enough to be susceptible to thermal (ultimately quantum decoherent) noise. In the second, available energy is focussed on a smaller subset of larger neurons whose action is deterministic. Possible implications for creative computing in silicon are discussed. Starting with a discussion of the concept of free will, the notion of consciousness is defined in terms of an awareness of what are perceived to be nearby counterfactual worlds in state space. It is argued that such awareness arises from an interplay between memories on the one hand, and quantum physical mechanisms (where, unlike in classical physics, nearby counterfactual worlds play an indispensable dynamical role) in the ion channels of neural networks, on the other. As with the brain’s susceptibility to noise, it is argued that in situations where quantum physics plays a role in the brain, it does so for reasons of energy efficiency. As an illustration of this definition of consciousness, a novel proposal is outlined as to why quantum entanglement appears to be so counter-intuitive.

Data Analytics for Creative Processes: Designing the Next Great Product

Problem Definition: Over the past decades, firms that develop new flavor and fragrance products (a $30 billion per year market) have amassed large amounts of data from their own internal creation processes. Yet, new product creation still mostly relies on human expertise and arduous experimentation. We present a data analytics framework to aid in the flavor and fragrance creation process. Practical Relevance: We describe general and fundamental algorithmic challenges for creating recipes. We address these challenges and propose an analytics framework to help product developers navigate the space of potential products that arises from combining ingredients and accelerate the overall development process. Methodology: The framework consists of two steps. In the first step, we use data to fit a metric over products, a procedure we refer to as curation. The metric of choice is the Earth Mover's Distance (EMD), where distances between products are quantified in terms of the pairwise similarity between ingredients. The curation process is formulated as a metric learning problem, where the cost matrix used in EMD computations is directly fit from labeled data. In the second step, we develop analytical tools to aid in the design of new products by sampling and evaluating new products within an (EMD) neighborhood of a seed product, a procedure we refer to as creation. Results: We introduce efficient algorithms for the curation and creation procedures. We derive parallel metric learning and k-NN search algorithms, an efficient sampling procedure, and an appropriate evaluation criterion across multiple metrics. We illustrate our results and product creation pipeline on open-access datasets. Managerial Implications: The methods we propose are new formulations and algorithms that address challenges that we observed as common across the innovation process of different flavor and fragrance firms, and may serve as an inspiration for a broader computational creativity approach used in industry.

Design and Evaluation of a Deep Learning Recommendation Based Augmented Reality System for Teaching Programming and Computational Thinking

Programming is considered a skill to arouse and inspire learner's potential. Learning to program is a complex process that requires students to write grammar and instructions. The structure of a programming language does not cause impose problems to students, the real obstacle is how to apply these learned grammars and present them in a complete and correct program code for problem solving. In this study, a deep learning recommendation system was developed, which includes augmented reality (AR) technology, and learning theory, and is provided for study by students in non-major and also from different learning backgrounds. Those students divided into two groups, the students participating in the experimental group were using the AR system with deep learning recommendation and the students participating in the control group were using the AR system without deep learning recommendation. The results show that students in experimental group perform better than the control group with regards to learning achievement. On the other hand, in the part of computational thinking ability, students using a deep learning recommendation based AR system is significantly better than those using non-deep learning recommendation based AR system. Among the various dimensions of computational thinking, creativity, logical computing, critical thinking, and problem-solving skills are significantly different among the two groups of students. The students in experimental group perform better than the control group with regards to the dimensions of computational thinking, creativity, logical computing, critical thinking, and problem-solving skills.

The Application of Artificial Intelligence in the Genetic Study of Alzheimer's Disease.

Alzheimer's disease (AD) is a neurodegenerative disease in which genetic factors contribute approximately 70% of etiological effects. Studies have found many significant genetic and environmental factors, but the pathogenesis of AD is still unclear. With the application of microarray and next-generation sequencing technologies, research using genetic data has shown explosive growth. In addition to conventional statistical methods for the processing of these data, artificial intelligence (AI) technology shows obvious advantages in analyzing such complex projects. This article first briefly reviews the application of AI technology in medicine and the current status of genetic research in AD. Then, a comprehensive review is focused on the application of AI in the genetic research of AD, including the diagnosis and prognosis of AD based on genetic data, the analysis of genetic variation, gene expression profile, gene-gene interaction in AD, and genetic analysis of AD based on a knowledge base. Although many studies have yielded some meaningful results, they are still in a preliminary stage. The main shortcomings include the limitations of the databases, failing to take advantage of AI to conduct a systematic biology analysis of multilevel databases, and lack of a theoretical framework for the analysis results. Finally, we outlook the direction of future development. It is crucial to develop high quality, comprehensive, large sample size, data sharing resources; a multi-level system biology AI analysis strategy is one of the development directions, and computational creativity may play a role in theory model building, verification, and designing new intervention protocols for AD.

A computational approach for using social networking platforms to support creative idea generation

Abstract Good design relies upon the generation of good ideas, but producing ideas, especially creative ones, is increasingly challenging. This may be due to limited relevant information, lack of creative skills, design fixation, or as a result of too many previously existing ideas. Conventional creativity tools, such as brainstorming and TRIZ, as well as advanced methods, such as design-by-analogy, are often employed by designers for idea generation to alleviate some of these challenges. In recent years, computational creativity tools have emerged to support creative idea generation. However, most of these computational tools are data-driven, and thereby employ various databases, for example, existing databases such as the ConceptNet containing past common-sense knowledge, and customized ones containing limited information. The limitations of these databases have constrained the capability of the computational creativity tools. Social media platforms, such as Twitter and Wikipedia, which allow users to create web-based content, have been reported to have billions of users. It can be considered a huge ‘unorganized’ database of information created by a crowd. However, to date little work has been done on the utilization of such crowd-generated knowledge from social media to support actual design activities, especially during the early stages of the design process. In this paper, the authors propose a computational approach to retrieve, process, and reuse the textual knowledge from social networks to prompt designers’ creative mind in producing ideas for new product design and development. They also propose a novel approach to construct crowd knowledge databases, which can be employed by computational tools, as well as used individually, for supporting creative idea generation. A case study involving the use of an existing social media analysis tool to construct a crowd database for helping designers produce ideas has been conducted to provide insights on implementing the proposed approach for creative idea generation.

Being a Realistic Master: Creating Props and Environments Design for AAA Games

To maximize the potential of computer games beyond entertainment, it is crucial to lower design and development costs and delegate production to domain specialists. While specialists may be interested in incorporating games, they often need more technical expertise to design or customize games for their requirements. To simplify game creation and improve user experience, we suggest defining games as a mixture of simpler games developed through combinatorial creativity. This method avoids the cognitive strain of learning a new design language. Along with speeding up game descriptions, designers might use a set of archetypical games to achieve their goals rather than starting from scratch. The design technique is enhanced by a game platform that provides authoring tools for exporting game designs to XML files and a game engine that automatically generates a 3D virtual world for play. This study explored how this approach allows designers to build games and evaluate their validity through play iteratively. Here, the combinatorial technique was assessed in two focus groups, demonstrating its viability and appeal among technical and non-technical users.

Functorial semiotics for creativity

In this paper, we develop a mathematically conceived semiotic theory. This project seems essential for a future computational creativity science since the outcome of the process of creativity must add new signs to given semiotic contexts. The mathematical framework is built upon categories of functors, in particular linearized categories deduced from path categories of digraphs and the Gabriel–Zisman calculus of fractions. Semantics in this approach is extended to a number of “global” constructions enabled by the Yoneda Lemma, including cohomological constructions. This approach concludes with a short discussion of classes of creativity with respect to the proposed functorial semiotics.

Computational Gastronomy - Use of Computing Methods in Culinary Creativity

Nowadays in culinary practices there is a great variety of regional cuisine in line with the cultural diversity of a place. This raises the question of whether there is a common pattern in determining the combination of food ingredients or the same principles in making recipes and producing certain tastes. For example, Western cuisine tends to use ingredients that have many flavor compounds, while East Asian cuisine tends to avoid ingredients sharing compounds. This study is driven by the results of previous studies showing the science of gastronomy is developing and producing the domain of computational gastronomy which contributes to the creation of recipes in innovative and creative ways. The purpose of this study is to understand the use of computational gastranomy in diverse food network in culinary creativity. The research design is exploring and looking for relationships between various aspects of food such as taste, aroma, seasoning, food ingredient, texture, and cooking methods. Cross sectional and longitudinal research are also carried out to find a causal relationship between computational gastronomy and culinary creation. The results showed that there was a relationship between various aspects, namely computational gastronomy, culinary creations, food content, and the use of technology in creating food recipes. The application of computational creativity in the culinary field can increase business value in the hotel kitchen area, the creation of recipes and food science.

High Noon on the Creative Frontier: Configuring Human and Machine Expertise

In 1960, CBS aired a special issue entitled “The Thinking Machine” which featured three Western playlets scripted by a computer programmed by MIT researchers. Almost 60 years later, two researchers at Autodesk used a computer program to help design a chair. In this article, I link these two seemingly discrete examples of computational creativity in order to highlight how digital fabrication technologies have served as an important test site for defining human and computational expertise. I do so by illustrating how concepts of “creativity” and “routine” were produced alongside the concepts of computational creativity during the development of digital fabrication. This dichotomy of “creative” and “routine” is not only used to determine the kinds of tasks that are appropriate for humans and computers to perform within the design and production process, but it is also used to render invisible the embodied craft knowledge required to substantiate these systems.

Computational Creativity Via Assisted Variational Synthesis of Mechanisms Using Deep Generative Models

Abstract Computational methods for kinematic synthesis of mechanisms for motion generation problems require input in the form of precision positions. Given the highly nonlinear nature of the problem, solutions to these methods are overly sensitive to the input—a small perturbation to even a single position of a given motion can change the topology and dimensions of the synthesized mechanisms drastically. Thus, the synthesis becomes a blind iterative process of maneuvering precision positions in the hope of finding good solutions. In this paper, we present a deep-learning-based framework which manages the uncertain user input and provides the user with a higher level control of the design process. The framework also imputes the input with missing information required by the computational algorithms. The approach starts by learning the probability distribution of possible linkage parameters with a deep generative modeling technique, called variational auto encoder (VAE). This facilitates capturing salient features of the user input and relating them with possible linkage parameters. Then, input samples resembling the inferred salient features are generated and fed to the computational methods of kinematic synthesis. The framework postprocesses the solutions and presents the concepts to the user along with a handle to visualize the variants of each concept. We define this approach as variational synthesis of mechanisms. In addition, we also present an alternate end-to-end deep neural network architecture for variational synthesis of linkages. This end-to-end architecture is a conditional-VAE, which approximates the conditional distribution of linkage parameters with respect to a coupler trajectory distribution. The outcome is a probability distribution of kinematic linkages for an unknown coupler path or motion. This framework functions as a bridge between the current state of the art theoretical and computational kinematic methods and machine learning to enable designers to create practical mechanism design solutions.

Effects of robotics programming on the computational thinking and creativity of elementary school students

Around the world, programming education is actively promoted by such factors as economic and technical requirements. The use of a robot in programming education could help students understand computer-science concepts more easily. In this study we designed a course in programming a robot for elementary school students and investigated its effectiveness by implementing it in actual classes. We further examined the effects of students’ prior skills and of gender on the outcomes. In addition, we reviewed the applicable teaching and learning strategies in the field of robotics programming. Our course in programming a robot was implemented for 155 Korean elementary school students in the fifth and sixth grades. The course was conducted for 11 weeks. Our results show that teaching programming by using a robot significantly improved computational thinking and creativity. Computational thinking, however, was not significantly improved in the group that initially showed high scores. Further, creativity was improved more in girls than in boys, and the mean difference was statistically significant, but the difference in computational thinking was not. The implication of this study is that the best approach is to design a course in programming a robot and apply it in actual classrooms in order to discuss teaching and learning strategies according to students’ prior skills and their gender.

Applying a description logic of typicality as a generative tool for concept combination in computational creativity

Applying a description logic of typicality as a generative tool for concept combination in computational creativity