Theoretical issues

As measured by the amount of activity in the field (eg, publications, conferences and workshops), computational creativity is a growing area of ​​research. ^{[ citation needed ]} But the field is still hampered by a number of fundamental problems. Creativity is very difficult, perhaps even impossible, to define in objective terms. Is it a state of mind, a talent or ability, or a process? Creativity takes many forms in human activity, some eminent (sometimes referred to as “Creativity” with a capital C) and some mundane .

These are problems that complicate the study of creativity in general, but certain problems attaching themselves to computational creativity: ^{[ citation needed ]}

• Can creativity be hard-wired? In existing systems to which creativity is attributed, is the creativity of the system or that of the system’s programmer or designer?
• How do we evaluate computational creativity? What counts as creativity in a computational system? Are natural language generation systems creative? Are machine translation systems creative? What distinguishes research in computational creativity from research into artificial intelligence ?
• If eminent creativity is about rule-breaking or the disavowal of convention, how is it possible for an algorithmic system to be creative? In essence, this is a variant of Ada Lovelace’s objection to machine intelligence, as recapitulated by modern theorists such as Teresa Amabile. ^[1] If a machine can only be programmed to do, how can its behavior ever be called creative ?

Indeed, not all computer theorists would agree that they could only be programmed to do ^[2] -a key point in favor of computational creativity.

Defining creativity in computational terms

Because no single perspective or a complete picture of creativity, the AI ​​researchers Newell, Shaw and Simon ^[3] developed the combination of novelty and usefulness in the cornerstone of a multi-pronged view of creativity, one that uses the following four criteria to categorize a given answer or solution as creative:

1. The answer is novel and useful (or for the individual or for society)
2. The answer demands that we reject ideas we had previously accepted
3. The answer results of intense motivation and persistence
4. The answer comes from clarifying a problem that was originally vague

“Top-down” approach to computational creativity, an alternative thread has been developed among “bottom-up” computational psychologists involved in artificial neural network research. During the late 1980s and early 1990s, such generative neural systems were driven by genetic algorithms. ^[4] Net recurrent involving experiments ^[5] were successful in hybridizing with simple musical melodies and predicting listener expectations.

One of the most popular psychologists in this field, Stephen Wolfram , who thought that the system was perceived as complex, including the mind ‘s creative output, could be considered as simple algorithms. As neuro-philosophical thinking matured, it also became apparent that it was actually presented to a scientific model of cognition, creative or not, because it was so important that it was more uplifting than accurate. So questions naturally arose as to how “rich,” “complex,” and “wonderful” creative cognition actually was. ^[6]

Artificial neural networks

Before 1989, artificial neural networks have been used to model certain aspects of creativity. Peter Todd (1989) first formed a neural network to reproduce musical melodies from a training set of musical pieces. Then he used a change algorithm to modify the network’s input parameters. The network was able to randomly generate new music in a highly uncontrolled manner. ^{[5] [7] [8]} In 1992, Todd ^[9] extended this work, using the so-called distal teacher approach that had been developed by Paul Munro, ^[10] Paul Werbos , ^[11] Nguyen D. and Bernard Widrow , ^[12] Michael I. Jordan and David Rumelhart. ^[13] In the new approach there are two neural networks, one of which is supplying training patterns to another. In later efforts by Todd, a composer would have a set of melodies that define the melody space, position them on a 2-d plane with a mouse-based graphic interface, and train a connectionist network to produce those melodies, and listen to the new “interpolated” melodies that the network corresponding to intermediate points in the 2-d plane.

More recently has neurodynamical model of semantic networks has-been Developed to study how the connectivity structure of These networks concerne un the richness of the semantic constructs, or ideas, They Can generate. It was Demonstrated That neural semantic networks That-have richer semantic dynamics than Those with other connectivity Structures May Provide Insight into the major issue of how the physical structure of the brain determined one of The Most Profound features of the human mind – its capacity for creative thought . ^[14]

Key concepts from the literature

Some high-level and philosophical themes recur throughout the field of computational creativity. ^{[ clarification needed ]}

Important categories of creativity

Margaret Boden ^[15] [16] Refers to creativity That Is novel Merely to the officer That Produces it as “P-creativity” (or “psychological creativity”), and Refers to creativity That Is Recognized As novel by society at large as ” H-creativity “(or” historical creativity “). Stephen Thaler has suggested a new category he calls “V-” or “Visceral creativity” creations machine architecture, with the “gateway” nets perturbed to produce alternative interpretations, and downstream nets shifting such interpretations to fit the overarching context. An important variety of such V-creativity is consciousness itself,^[17]

Exploratory and transformational creativity

Boden also distinguishes between creativity and arises from an exploration within an established conceptual space, and the creativity that arises from a deliberate transformation or transcendence of this space. She labels the train as exploratory creativity and the latter as transformational creativity, see the latter as a form of creativity far more radical, challenging, and rarer than the former. Following the criteria from Newell and Simon elaborated above, we believe that it is a good practice to understood space (criterion 3) – while transformational creativity should involve the rejection of some of the constraints that define this space (criterion 2) or some of the assumptions that define the problem itself (criterion 4). Boden’s insights in the field of computational engineering, providing a more informative touchstone for development work than a technical framework of algorithmic substance. However, Boden ‘^[18]

Generation and evaluation

The criterion that creative products should be invented and used in the creative process. In the first phase, novel (to the system itself, thus P-Creative) constructs are generated; unoriginal constructs that are already known to the system at this stage. This body of potential creative constructs are then evaluated, to determine which are meaningful and useful. This two-phase structure conforms to the Gene model of Finke, Ward and Smith, ^[19] which is a psychological model of creative generation based on empirical observation of human creativity.

Combinatorial creativity

A great deal, perhaps all, of human creativity can be understood as a novel combination of pre-existing ideas or objects ^{[ citation needed ]} . Common strategies for combinatorial creativity include:

• Placing a familiar object in an unfamiliar setting (eg, Marcel Duchamp ‘s Fountain ) or an unfamiliar object in a familiar setting (eg, a fish-out-of-water story Such As The Beverly Hillbillies )
• Blending two superficially different objects or genres (eg, a sci-fi story set in the Wild West, with robot cowboys, as in Westworld , or the reverse, as in Firefly , Japanese haiku poems, etc.)
• Comparing a familiar object to a superficially unrelated and semantically distant concept (eg, “Makeup is the Western burka “; “A zoo is a gallery with living exhibits”)
• Adding a new and unexpected feature to an existing concept (eg, Adding a scalpel to a Swiss Army knife ; Adding a camera to a mobile phone )
• Two incongruous scenarios in the same narrative to get a joke (eg, the Emo Philips joke “Women are always using their careers.” Damned anthropologists! “)
• Using an image of a product or a product (eg, using the Marlboro Man to sell cars, or to advertise the dangers of smoking-related impotence).

The combinatorial perspective allows us to model creativity as possible through the space of possible combinations. The combinations can be made from a composition or concatenation of different representations, or through a rule-based or stochastic transformation of initial and intermediate representations. Genetic algorithms and neural networks can be used to generate or crossover representations that capture a combination of different inputs.

Conceptual blending

Mark Turner and Gilles Fauconnier ^[20] [21] proposes a model called Expired Conceptual Integration Networks That elaborates upon Arthur Koestler ‘s ideas about creativity ^[22] as well as more recent work by Lakoff and Johnson, ^[23] by Synthesizing ideas from Cognitive Linguistic research into mental spaces and conceptual metaphors . Their basic model defines an integration network

• A first input space (contains one conceptual structure or mental space)
• A second input space (to be blended with the first input)
• A generic space of stock conventions and image-schemas that allow the input spaces to be understood from an integrated perspective
• A blend of space in which the following elements are combined; inferences arising from this combination also resides here, which leads to emergent structures that conflict with the inputs.

Fauconnier and Turner describe a collection of optimality principles that are claimed to guide the construction of a well-formed integration network. In essence, they can be compressed into a single structure. This compression operates on the level of conceptual relations. For example, a series of similar relations between the input spaces can be compressed into a single identity relationship in the blend.

Some computational success has been achieved by extending pre-existing computational models of analogical mapping. ^[24] More recently, Francisco Câmara Pereira ^[25] presented an implementation of blending theory that employs ideas both of GOFAI and genetic algorithms to achieve some aspects of blending theory in a practical form; his example is one of the most important areas of the history of visualization, and the third most frequent includes the creation of mythical monsters by combining 3-D graphical models.

Linguistic creativity

Language provides continuous opportunity for creativity, evident in the generation of novel sentences, phrasing, puns , neologisms , rhymes , allusions , sarcasm , irony , similes , metaphors , analogies , witticisms , and jokes . Native speakers of morphologically rich languages ​​often create new word-forms that are easily understood, they will never find their way to the dictionary. The area of natural language generation has been studied, but these creative aspects of everyday life have to be built with any robustness or scale.

Story generation

Substantial work has been conducted in the area of ​​linguistic creation since 1970s, with the development of James Meehan’s TALE-SPIN ^[26] system. TALE-SPIN: Stories of a problem-based narrative, storytelling, storytelling, storytelling, storytelling, storytelling, storytelling, storytelling. The MINSTREL ^[27] system represents a complex elaboration of this basis approach, distinguishing a range of character-level goals in the story from a range of author-level goals for the story. Systems like Bringsjord’s BRUTUS ^[28]elaborate these ideas further to create stories with complex inter-personal themes like betrayal. Nonetheless, MINSTREL explicitly models the creative process with a set of Transform Recall Adapt Methods (TRAMs) to create novel scenes from old. The MEXICA ^[29] model of Rafael Pérez y Perez and Mike Sharples is more explicitly interested in the creative process of storytelling, and implements a version of the engagement-reflection cognitive model of creative writing.

The company Narrative Science makes computer generated news and reports commercially available, including summarizing team sporting events based on statistical data from the game. It also creates financial reports and real estate analyzes. ^[30]

Metaphor and simile

Example of a metaphor: “She was an ape.”

Example of a simile: “Felt like a tiger-fur blanket. ” The computational study of these phenomena has been focused on a knowledge-based process. Computationalists such as Yorick Wilks , James Martin, ^[31] Dan Fass, John Barnden, ^[32] and Mark Lee have developed knowledge-based approaches to the processing of metaphors, or at a linguistic level or a logical level. Tony Veale and Yanfen Hao have developed a system, called Sardonicus, that acquires a comprehensive database of explicit similes from the web; These similes are then tagged as bona-fide (eg, “as hard as steel”) or ironic (eg, “as hairy bowling ball “, “as pleasant as a root canal””); Similes of Either kind can be retrieved on demand for Any Given adjective They use thesis similes as the basis of an on-line metaphor generation system called Aristotle. ^[33] That can suggest lexical metaphors for a descriptive Given goal (eg, to describe a supermodel as skinny, the source terms “pencil”, “whip”, ” whippet “, “rope”, ” stick-insect ” and “snake” are suggested).

Analogy

The process of analogical reasoning has been studied from a mapping perspective and a retrieval perspective, the latter being key to the generation of novel analogies. The dominant school of research, as advanced by Dedre Gentner , analogy as a structure-preserving process; this view has-been Implemented in the mapping engine structure or EMS, ^[34] the MAC / FAC retrieval engine (Many Are Called, Few Are Chosen), ACME ( Analogical Constraint Mapping Engine ) and ARC ( Analogical Retrieval Constraint System ). Other mapping-based approaches include Sapper, ^[24]which situates the mapping process in a semantic-network model of memory. Analogy is a very active sub-area of ​​creative computation and creative cognition; active in this sub-area include Douglas Hofstadter , Paul Thagard , and Keith Holyoak . Also worthy of note here is Peter Turney and Michael Littman’s machine learning approach to solving SAT -style analogy problems; Their approach achieves a score that compares well with average scores achieved by humans on these tests.

Joke generation

Humor is an especially knowledge-hungry process, and the most successful joke-generation systems to date have been punished, as exemplified by the work of Kim Binsted and Graeme Ritchie. ^[35] This work includes the JAPEsystem, which can generate a wide range of young people. An improved version of JAPE has been developed in the context of the STANDUP system, which has been experimentally deployed as a means of enhancing linguistic interaction with children with communication disabilities. Some limited progress has been made in generating humor, which involves other aspects of natural language, such as the deliberate misunderstanding of pronominal reference (in the work of Hans Wim Tinholt and Anton Nijholt), as well as in the generation of humorous acronyms in the HAHAcronym system ^[36] of Oliviero Stock and Carlo Strapparava.

Neologism

The blending of multiple word forms is a dominant force for new word creation in language; These new words are commonly called “blends” or ” portmanteau words ” (after Lewis Carroll ). Tony Veale has developed a system called ZeitGeist ^[37] that harvests neological headwords from Wikipedia and interprets them related to their local context in Wikipedia and relates to specific word senses in WordNet. ZeitGeist has been extended to generate neologisms of its own; These are the words that are used in the context of these words (eg, “food traveler” for “gastronaut” and “time traveler” for ” chrononaut “). Then it uses Web search to determine qui qui glosses are Meaningful and neologisms have-nots-been used before; this search identifies the subset of these words that are both novel (“H-creative”) and useful. Neurolinguistic inspirations have been used to analyze the process of novel word creation in the brain, ^[38] understand neurocognitive processes responsible for intuition, insight,^[39] and to create a new type of invention, based on their description. ^[40] Further, the Nehovah system ^[41] blends two sources words into a neologism that blends the meanings of the two source words. Nehovah searches for WordNet for synonyms and TheTopTens.com for pop culture hyponyms. The synonyms and hyponyms are blended together to create a set of candidate neologisms. Theologisms are then based on their word structure, how is the word being, how is the concept of the concept of the subject? Nehovah loosely follows conceptual blending.

Poetry

Like jokes, poems involve a complex interaction of different constraints, and no general-purpose poem generator, the combination of meaning, phrasing, structure and rhyme aspects of poetry. Nonetheless, Pablo Gervás ^[42] has developed a noteworthy system called ASPERA that employs a case-based reasoning (CBR) approach to generating poetic formulations of a given input text via a composition of poetic fragments that are retrieved from a case-base of existing poems. Each poem fragment in the ASPERA case-base is annotated with a prose string that expresses the meaning of the fragment, and this prose string is used as the key for each fragment. Metrical rules are then used to combine these fragments into a well-formed poetic structure.Racter is an example of such a software project.

Musical creativity

Computational creativity in the field of music has been discussed in the field of music and music. The domain of generation has included classical music (with software of Mozart and Bach ) and jazz ^[43] . Most notably, David Cope ^[44] has written a software system called “Experiments in Musical Intelligence” (or “EMI”) ^[45]that is capable of analyzing and generalizing from existing music by a composer in the same style. EMI’s output is convincing enough to persuade human listeners that its music is human-generated to a high level of competence. ^[46]

In the field of contemporary classical music, I am the first computer that composes from scratch, and produces final scores that professional interpreters can play. The London Symphony Orchestra played a piece for full orchestra, included in Iamus’ debut CD , ^[47] which New Scientist described as “The first major work composed by a computer and performed by a full orchestra”. ^[48] Melomics , the technology behind Iamus, is able to generate pieces in different styles of music with a similar level of quality.

Creativity research in jazz has focused on the process of improvisation and the cognitive demands of this type of music. ^{[ citation needed ]} The Shimon robot, developed by Gil Weinberg of Tech Georgia, has demonstrated jazz improvisation. ^[49] OMax, SoMax and PyOracle, are used to create improvisations in real-time by re-injecting variable length sequences learned on the fly from live performer. ^[50]

In 1994, a Creativity Machine architecture (see above) was able to generate 11,000 musical hooks by training a synaptically disturbed neural net on 100 melodies that had appeared on the top ten list over the last 30 years. In 1996, a self-bootstrapping machine Creativity Machine experienced audience facial expressions through an advanced machine vision system and perfected its musical talents to generate an album entitled “Song of the Neurons” ^[51]

In the field of musical composition, the patented works ^[52] by René-Louis Baron (1998) . All of a kind in the world of music and the effects of music (in real time while listening to the song). The patented invention Medal-Composerraises problems of copyright.

Visual and artistic creativity [ edit]

Computational creativity in the generation of visual art has had some notable successes in the creation of both abstract art and representational art. The most famous program in this domain is Harold Cohen ‘s AARON , ^[53] which has been continuously developed and expanded since 1973. Though formulaic, Aaron exhibits a range of outputs, generating black-and-white drawings figures (such as dancers), potted plants, rocks, and other elements of background imagery. These images are of a high quality to be displayed in reputable galleries.

Other software artists include the NEvAr system (for “Neuro-Evolutionary Art”) of Penousal Machado. ^[54] NEvAr uses a genetic algorithm to derive a mathematical function that is then used to generate a colored three-dimensional surface. A human user is allowed to select the best pictures after each phase of the genetic algorithm, and these preferences are used to guide successive phases, thus pushing the search engine into the most appealing to the user.

The Painting Fool , produced by Simon Colton, is a picture of a painting of different colors, color palettes and brush types. This article looks at the source of information on the subject of art, the earliest iterations of painting. Nonetheless, in more recent work, The Painting Fool has been extended, AARONdoes, from its own limited imagination. Images in this vein include cityscapes and forests, which are generated by a process of constraint satisfaction from some basic scenarios provided by the user (eg, saturated, while those should be less saturated and appear smaller). Artistically, the images now created by the Painting Fool appear on by those created by Aaron, though the extensible mechanisms employed by the trainer (constraint satisfaction, etc.) may well allow it to be developed and developed.

The artist Krasimira Dimtchevska and the software developer Svillen Ranev have created a computational system combining a rule-based generator of English sentences and a visual composition that converts sentences generated by the system into abstract art. ^[55] The software generates automatically indefinite number of different images using different color, shape and size palettes. The software also allows the user to select the subject of the generated sentences or the one of the pallets used by the visual composition builder.

An emerging area of ​​computational creativity is that of video games. ANGELINA is a system for creatively developing video games in Java by Michael Cook. One important aspect is Mechanic Miner, a system that can generate simple game mechanics. ^[56] ANGELINA can evaluate these mechanics for usefulness by playing simple unsolvable game levels and testing to see if the new mechanic makes the level solvent. Sometimes Mechanic Miner discovers bugs in the code and exploits to solve problems with. ^[57]

In July 2015 Google released DeepDream – an open source ^[58] computer vision program, which is used to detect convoluted neural network to find and enhance patterns in images via algorithmic pareidolia , thus creating a dreamlike psychedelic appearance in the deliberately over-processed images. ^{[59] [60] [61]}

In August 2015 researchers from Tübingen, Germany, a convolutional neural network that uses neural representations to recombine content and style of arbitration images which is able to turn images into stylistic imitations of works of art by artists such as Picasso or Van Gogh in about an hour. Their algorithms can be used in the website DeepArt that allows users to create unique artistic images by their algorithm. ^{[62] [63] [64] [65]}

In early 2016, a global team of researchers explained how to understand the digital synaptic neural substrate (DSNS), which could be used to derive original chess puzzles that were not derived from endgame databases. ^[66] The DSNs is reliable to combine features of different objects (eg chess problems, paintings, music) using stochastic methods in order to drift specifications qui new feature can be used to generate objects in’any of the original domains. The generated chess puzzles have been featured on YouTube. ^[67]

Creativity in problem solving

Creativity is also useful in allowing for unusual solutions in problem solving . In psychology and cognitive science , this research area is called creative problem solving . The Explicit-Implicit Interaction (EII) theory of creativity has been implemented using a CLARION -based computational model that allows for simulation of incubation and insight in problem solving. ^[68] The emphasis of this computational creativity is not in performance (as in artificial intelligenceprojects) but rather on the explanation of the psychological processes leading to human creativity and the reproduction of data collected in psychology experiments. So far, this project has been successful in providing an explanation for incubation effects in simple memory experiments, insight in problem solving, and reproducing the overshadowing effect in problem solving.

Debate about “general” theories of creativity

Some researchers feel that creativity is a complex phenomenon which is more complicated by the plasticity of the language we use to describe it. We can describe not just the agent of creativity as “creative” but also the product and the method. Consequently, it could be claimed that it is unrealistic to speak of a general theory of creativity . ^{[ citation needed ]} Nonetheless, some generative principles are more general than others, leading some advocates to claim that certain computational approaches are “general theories”. Stephen Thaler, for instance, proposes that certain modalities of neural networks are generative enough, and general enough, to manifest a high degree of creative capabilities. Likewise, the Formal Theory of Creativity^[69] [70] is based was single computational principle published by Jürgen Schmidhuber in 1991. ^[71] The theory postulates That creativity and curiosity and selective focus in general are by-products of a single algorithmic principle for measuring and Optimizing learning progress .

Unified model of creativity

A unifying model of creativity ^[72] was proposed by SL Thaler through a series of international patents in computational creativity, beginning in 1997 with the issuance of US Patent 5,659,666. ^[73] Based upon theoretical studies of neural traumatized networks and inspired by studies of damage-induced vibrational modes in simulated crystal lattices, ^[74] this extensive intellectual property subsequently taught the implementation of a broad ranks of noise, damage, and disordering effects to has trained neural network so as to drive the formation of novel or confabulatory patterns ^{[75] [76] [77] [78] [79] [80] [81] [82]} that could be considered

Thaler’s Scientific and Philosophical Papers The following issue of these patents describes:

1. The aspects of cognition accompanying a broad gamut of cognitive functions (eg, waking to dreaming to near-death trauma), ^{[83] [84] [85]}
2. A shorthand notation for describing creative neural architectures and their function, ^[86]
3. Quantitative modeling of the rhythm with which creative cognition occurs, ^{[72] [87] [88]} and,
4. A prescription for critical disruption regimes leading to the most efficient generation of useful information by a creative neural system. ^{[87] [88] [89]}
5. A bottom-up model that links creativity and a wide range of psychopathologies. ^[90]

Thaler has also recruited his generative neural architectures into a theory of consciousness that is closely related to the temporal evolution of thought, while also accounting for the subjective feeling associated with this hotly debated mental phenomenon. ^{[72] [87] [91] [92] [93] [88] [94]}

In 1989, one of the most controversial reductions in this general theory of creativity, ^[72] one neural net termed the “grim reaper,” governed the synaptic damage (ie, rule-changes) applied to another net that had learned a series of traditional Christmas carol lyrics. The train net, on the lookout for both novel and grammatical lyrics, seized upon the chilling sentence, “In the end, to the earth in one eternal silent night,” thereafter ceasing the synaptic degradation process. In subsequent projects, these systems are often used for the purpose of learning and learning, oftentimes bootstrapping their learning from a blank slate based on the success or failure of self-conceived concepts and strategies. ^[95]

Criticism of Computational Creativity

Traditional computers, et al. (1992), 1992, pp. 251-322, adapted to be used in the computational creativity application, as they are fundamentally transform a discrete set of discrete, limited domain of input parameters. As such, a computer can not be creative, as everything in the output has already been present in the data or the algorithms. For some related discussions and references to related work is captured in some recent work on philosophical foundations of simulation ^[96] .

Mathematically, the same set of arguments against creativity has been made by Chaitin ^[97] . Similar observations come from a Model Theory perspective. All this criticism emphasizes that computational creativity is useful, but it is not real creativity, just nothing new is created, just transformed in well defined algorithms.

Events

The International Conference on Computational Creativity (ICCC), annually organized by The Association for Computational Creativity . Events in the series include:

• ICCC 2017, Atlanta, Georgia, USA
• ICCC 2016, Paris, France
• ICCC 2015, Park City, Utah, USA. Keynote: Emily Short
• ICCC 2014, Ljubljana, Slovenia. Keynote: Oliver Deussen
• ICCC 2013, Sydney, Australia. Keynote: Arne Dietrich
• ICCC 2012, Dublin, Ireland. Keynote: Steven Smith
• ICCC 2011, Mexico City, Mexico. Keynote: George E Lewis
• ICCC 2010, Lisbon, Portugal. Keynote / Inivited Talks: Nancy J Nersessian and Mary Lou Maher

Previously, the community of computational creativity has held a dedicated workshop, the International Joint Workshop on Computational Creativity, every year since 1999. ^{[ citation needed ]}

• IJWCC 2003, Acapulco, Mexico, as part of IJCAI’2003
• IJWCC 2004, Madrid, Spain, as part of ECCBR’2004
• IJWCC 2005, Edinburgh, UK, as part of IJCAI’2005
• IJWCC 2006, Riva del Garda, Italy, as part of ECAI’2006
• IJWCC 2007, London, UK, has a stand-alone event
• IJWCC 2008, Madrid, Spain, has a stand-alone event

The 1st Conference on Computer Simulation of Musical Creativity will be held

• CCSMC 2016, ^[98] June 17-19, University of Huddersfield, UK. Keynotes: Geraint Wiggins and Graeme Bailey.

Publications and forums

Design Computing and Cognition is a conference that addresses computational creativity. The ACM Creativity and Cognition is another forum for issues related to computational creativity. Computer Science Days 2016 keynote by Shlomo Dubnov was on Theoretic Creativity. ^[99]

A number of recent books provide a good introduction or a good overview of the field of Computational Creativity. These include:

• Pereira, FC (2007). “Creativity and Artificial Intelligence: A Conceptual Blending Approach”. Applications of Cognitive Linguistics series, Mutton de Gruyter.
• Veale, T. (2012). “Exploding the Creativity Myth: The Computational Foundations of Linguistic Creativity”. Bloomsbury Academic, London.
• McCormack, J. and Inverno, M. (eds.) (2012). “Computers and Creativity”. Springer, Berlin.
• Veale, T., Feyaerts, K. and Forceville, C. (2013, forthcoming). “Creativity and the Agile Mind: A Multidisciplinary study of a multifaceted phenomenon”. Sheep of Gruyter.

In addition to the proceedings of conferences and workshops, the computational creativity community

• New Generation Computing , Volume 24, Issue 3, 2006
• Journal of Knowledge-Based Systems , Volume 19, Issue 7, November 2006
• AI Magazine , Volume 30, Number 3, Fall 2009
• Minds and Machines , volume 20, number 4, November 2010
• Cognitive Computation , volume 4, issue 3, September 2012
• AIEDAM , volume 27, number 4, Fall 2013
• Computers in Entertainment , two special issues on Meta-Creation Music (MuMe), Fall 2016 (forthcoming)

In addition to these, a new journal has started which focuses on computational creativity within the field of music.

• JCMS 2016, Journal of Creative Music Systems