Computational creativity

Computational creativity

Computational creativity (also known as artificial creativity, mechanical creativity or creative computation) is a multidisciplinary endeavour that is located at the intersection of the fields of artificial intelligence, cognitive psychology, philosophy, and the arts.

The goal of computational creativity is to model, simulate or replicate creativity using a computer, to achieve one of several ends:

  • To construct a program or computer capable of human-level creativity.
  • To better understand human creativity and to formulate an algorithmic perspective on creative behavior in humans.
  • To design programs that can enhance human creativity without necessarily being creative themselves.

The field of computational creativity concerns itself with theoretical and practical issues in the study of creativity. Theoretical work on the nature and proper definition of creativity is performed in parallel with practical work on the implementation of systems that exhibit creativity, with one strand of work informing the other.


  • Theoretical issues 1
  • Defining creativity in computational terms 2
  • Artificial Neural Networks 3
  • Key concepts from the literature 4
    • Important categories of creativity 4.1
    • Exploratory and transformational creativity 4.2
    • Generation and evaluation 4.3
    • Combinatorial creativity 4.4
      • Conceptual blending 4.4.1
  • Linguistic creativity 5
    • Story generation 5.1
    • Metaphor and simile 5.2
    • Analogy 5.3
    • Joke generation 5.4
    • Neologisms 5.5
    • Poetry 5.6
  • Musical creativity 6
  • Visual and artistic creativity 7
  • Creativity in problem solving 8
  • Debate about "general" theories of creativity 9
    • Stephen L. Thaler's work on a unified model of creativity 9.1
  • Events 10
  • Publications and Forums 11
  • See also 12
  • References 13
  • External links 14

Theoretical issues

As measured by the amount of activity in the field (e.g., publications, conferences and workshops), computational creativity is a growing area of research. 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 attach themselves specifically to computational creativity:

  • Can creativity be hard-wired? In existing systems to which creativity is attributed, is the creativity that 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 in artificial intelligence generally?
  • 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 do only what it was programmed to do, how can its behavior ever be called creative?

Indeed, not all computer theorists would agree with the premise that computers can only do what they are programmed to do[2]—a key point in favor of computational creativity.

Defining creativity in computational terms

Because no single perspective or definition seems to offer a complete picture of creativity, the AI researchers Newell, Shaw and Simon[3] developed the combination of novelty and usefulness into 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 (either for the individual or for society)
  2. The answer demands that we reject ideas we had previously accepted
  3. The answer results from intense motivation and persistence
  4. The answer comes from clarifying a problem that was originally vague

Whereas the above reflects a "top-down" approach to computational creativity, an alternative thread has developed among "bottom-up" computational psychologists involved in artificial neural network research. During the late 1980s and early 1990s, for example, such generative neural systems were driven by genetic algorithms.[4] Experiments involving recurrent nets[5] were successful in hybridizing simple musical melodies and predicting listener expectations.

Concurrent with such research, a number of computational psychologists took the perspective, popularized by Stephen Wolfram, that system behaviors perceived as complex, including the mind’s creative output, could arise from what would be considered simple algorithms. As neuro-philosophical thinking matured, it also became evident that language actually presented an obstacle to producing a scientific model of cognition, creative or not, since it carried with it so many unscientific aggrandizements that were more uplifting than accurate. Thus 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 trained 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] D. Nguyen 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 select 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 generates corresponding to intermediate points in the 2-d plane.

More recently a neurodynamical model of semantic networks has been developed to study how the connectivity structure of these networks relates to the richness of the semantic constructs, or ideas, they can generate. It was demonstrated that semantic neural networks that have richer semantic dynamics than those with other connectivity structures may provide insight into the important issue of how the physical structure of the brain determines 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.

Important categories of creativity

Margaret Boden[15][16] refers to creativity that is novel merely to the agent 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" wherein significance is invented to raw sensory inputs to a Creativity 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, wherein meaning is reflexively invented to activation turnover within the brain[17]

Exploratory and transformational creativity

Boden also distinguishes between the creativity that 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 former as exploratory creativity and the latter as transformational creativity, seeing 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 can see that both forms of creativity should produce results that are appreciably novel and useful (criterion 1), but exploratory creativity is more likely to arise from a thorough and persistent search of a well-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 have guided work in computational creativity at a very general level, providing more an inspirational touchstone for development work than a technical framework of algorithmic substance. However, Boden’s insights are more recently also the subject of formalization, most notably in the work by Geraint Wiggins.[18]

Generation and evaluation

The criterion that creative products should be novel and useful means that creative computational systems are typically structured into two phases, generation and evaluation. In the first phase, novel (to the system itself, thus P-Creative) constructs are generated; unoriginal constructs that are already known to the system are filtered at this stage. This body of potentially creative constructs are then evaluated, to determine which are meaningful and useful and which are not. This two-phase structure conforms to the Geneplore 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. Common strategies for combinatorial creativity include:

  • Placing a familiar object in an unfamiliar setting (e.g., Marcel Duchamp's Fountain) or an unfamiliar object in a familiar setting (e.g., a fish-out-of-water story such as The Beverly Hillbillies)
  • Blending two superficially different objects or genres (e.g., 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 (e.g., "Makeup is the Western burka"; "A zoo is a gallery with living exhibits")
  • Adding a new and unexpected feature to an existing concept (e.g., adding a scalpel to a Swiss Army knife; adding a camera to a mobile phone)
  • Compressing two incongruous scenarios into the same narrative to get a joke (e.g., the Emo Philips joke "Women are always using me to advance their careers. Damned anthropologists!")
  • Using an iconic image from one domain in a domain for an unrelated or incongruous idea or product (e.g., using the Marlboro Man image to sell cars, or to advertise the dangers of smoking-related impotence).

The combinatorial perspective allows us to model creativity as a search process through the space of possible combinations. The combinations can arise from 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 blended or crossover representations that capture a combination of different inputs.

Conceptual blending

Mark Turner and Gilles Fauconnier[20][21] propose a model called 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 as four connected spaces:

  • 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 space in which a selected projection of elements from both input spaces are combined; inferences arising from this combination also reside here, sometimes leading 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 see blending as a compression mechanism in which two or more input structures are compressed into a single blend structure. This compression operates on the level of conceptual relations. For example, a series of similarity relations between the input spaces can be compressed into a single identity relationship in the blend.

Some computational success has been achieved with the blending model by extending pre-existing computational models of analogical mapping that are compatible by virtue of their emphasis on connected semantic structures.[24] More recently, Francisco Câmara Pereira[25] presented an implementation of blending theory that employs ideas both from GOFAI and genetic algorithms to realize some aspects of blending theory in a practical form; his example domains range from the linguistic to the visual, and the latter most notably 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, phrasings, puns, neologisms, rhymes, allusions, sarcasm, irony, similes, metaphors, analogies, witticisms, and jokes. Native speakers of morphologically rich languages frequently create new word-forms that are easily understood, although they will never find their way to the dictionary. The area of natural language generation has been well studied, but these creative aspects of everyday language have yet to be incorporated with any robustness or scale.

Story generation

Substantial work has been conducted in this area of linguistic creation since the 1970s, with the development of James Meehan's TALE-SPIN [26] system. TALE-SPIN viewed stories as narrative descriptions of a problem-solving effort, and created stories by first establishing a goal for the story’s characters so that their search for a solution could be tracked and recorded. 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 Pérez 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 analyses.[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 mainly focused on interpretation as 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, either 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 (e.g., "as hard as steel") or ironic (e.g., "as hairy as a bowling ball", "as pleasant as a root canal"); similes of either type can be retrieved on demand for any given adjective. They use these similes as the basis of an on-line metaphor generation system called Aristotle[33] that can suggest lexical metaphors for a given descriptive goal (e.g., to describe a supermodel as skinny, the source terms “pencil”, “whip”, “whippet”, “rope”, “stick-insect” and “snake” are suggested).


The process of analogical reasoning has been studied from both a mapping and a retrieval perspective, the latter being key to the generation of novel analogies. The dominant school of research, as advanced by Dedre Gentner, views analogy as a structure-preserving process; this view has been implemented in the structure mapping engine or SME,[34] the MAC/FAC retrieval engine (Many Are Called, Few Are Chosen), ACME (Analogical Constraint Mapping Engine) and ARCS (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 figures 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 the solving of SAT-style analogy problems; their approach achieves a score that compares well with average scores achieved by humans on these tests.

Joke generation

Humour is an especially knowledge-hungry process, and the most successful joke-generation systems to date have focussed on pun-generation, as exemplified by the work of Kim Binsted and Graeme Ritchie.[35] This work includes the JAPE system, which can generate a wide range of puns that are consistently evaluated as novel and humorous by young children. An improved version of JAPE has been developed in the guise 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 humour that 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.


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 WorldHeritage and interprets them relative to their local context in WorldHeritage and relative to specific word senses in WordNet. ZeitGeist has been extended to generate neologisms of its own; the approach combines elements from an inventory of word parts that are harvested from WordNet, and simultaneously determines likely glosses for these new words (e.g., "food traveller" for "gastronaut" and "time traveller" for "chrononaut"). It then uses Web search to determine which glosses are meaningful and which neologisms have not been used before; this search identifies the subset of generated 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, imagination and creativity[39] and to create a server that invents novel names for products, based on their description.[40] Further, the system Nehovah[41] blends two source words into a neologism that blends the meanings of the two source words. Nehovah searches WordNet [42] for synonyms and to search for pop culture hyponyms. The synonyms and hyponyms are blended together to create a set of candidate neologisms. The neologisms are then scored based on their word structure, how unique the word is, how apparent the concepts are conveyed, and if the neologism has a pop culture reference. Nehovah loosely follows conceptual blending. It can be accessed at


More than iron, more than lead, more than gold I need electricity.
I need it more than I need lamb or pork or lettuce or cucumber.
I need it for my dreams. Racter, from The Policeman's Beard Is Half Constructed

Like jokes, poems involve a complex interaction of different constraints, and no general-purpose poem generator adequately combines the meaning, phrasing, structure and rhyme aspects of poetry. Nonetheless, Pablo Gervás[43] 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 retrieval 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 music domain has focused both on the generation of musical scores for use by human musicians, and on the generation of music for performance by computers. The domain of generation has included classical music (with software that generates music in the style of Mozart and Bach) and jazz. 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 human composer to generate novel musical compositions 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, Iamus is 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 that this places on a musical agent: reasoning about time, remembering and conceptualizing what has already been played, and planning ahead for what might be played next. The robot Shimon, developed by Gil Weinberg of Georgia Tech, has demonstrated jazz improvisation.[49]

In 1994, a Creativity Machine architecture (see above) was able to generate 11,000 musical hooks by training a synaptically perturbed neural net on 100 melodies that had appeared on the top ten list over the last 30 years. In 1996, a self-bootstrapping Creativity Machine observed audience facial expressions through an advanced machine vision system and perfected its musical talents to generate an album entitled "Song of the Neurons"[50]

In the field of musical composition, the patented works[51] by René-Louis Baron allowed to make a robot that can create and play a multitude of orchestrated melodies so-called "coherent" in any musical style. All outdoor physical parameter associated with one or more specific musical parameters, can influence and develop each of these songs (in real time while listening to the song). The patented invention Medal-Composer raises problems of copyright.

Visual and artistic creativity

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,[52] which has been continuously developed and augmented since 1973. Though formulaic, Aaron exhibits a range of outputs, generating black-and-white drawings or colour paintings that incorporate human figures (such as dancers), potted plants, rocks, and other elements of background imagery. These images are of a sufficiently high quality to be displayed in reputable galleries.

Other software artists of note include the NEvAr system (for "Neuro-Evolutionary Art") of Penousal Machado.[53] NEvAr uses a genetic algorithm to derive a mathematical function that is then used to generate a coloured 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, thereby pushing NEvAr’s search into pockets of the search space that are considered most appealing to the user.

The Painting Fool, developed by Simon Colton originated as a system for overpainting digital images of a given scene in a choice of different painting styles, colour palettes and brush types. Given its dependence on an input source image to work with, the earliest iterations of the Painting Fool raised questions about the extent of, or lack of, creativity in a computational art system. Nonetheless, in more recent work, The Painting Fool has been extended to create novel images, much as AARON does, 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 (e.g., these scenarios allow the system to infer that objects closer to the viewing plane should be larger and more color-saturated, while those further away should be less saturated and appear smaller). Artistically, the images now created by the Painting Fool appear on a par with those created by Aaron, though the extensible mechanisms employed by the former (constraint satisfaction, etc.) may well allow it to develop into a more elaborate and sophisticated painter.

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 builder that converts sentences generated by the system into abstract art.[54] 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/and the one or more of the palettes 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 which can generate short segments of code which act as simple game mechanics.[55] ANGELINA can evaluate these mechanics for usefulness by playing simple unsolvable game levels and testing to see if the new mechanic makes the level solvable. Sometimes Mechanic Miner discovers bugs in the code and exploits these to make new mechanics for the player to solve problems with.[56]

In July 2015 Google released DeepDream – an open source[57] computer vision program, created to detect faces and other patterns in images with the aim of automatically classifying images, which uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dreamlike psychedelic appearance in the deliberately over-processed images.[58][59][60]

In August 2015 researchers from Tübingen, Germany created a convolutional neural network that uses neural representations to separate and recombine content and style of arbitrary images which is able to turn images into stylistic imitations of works of art by artists such as a Picasso or Van Gogh in about an hour.[61][62][63][64]

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 recently been implemented using a CLARION-based computational model that allows for the simulation of incubation and insight in problem solving.[65] The emphasis of this computational creativity project is not on performance per se (as in artificial intelligence projects) 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 whose study is further 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 given the amorphousness of the concept, the plasticity of the language, and the tendency of our cultural perspectives on the concept to evolve over time.

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[66][67] is based on a simple computational principle published by Jürgen Schmidhuber in 1991.[68] The theory postulates that creativity and curiosity and selective attention in general are by-products of a simple algorithmic principle for measuring and optimizing learning progress.

Popular wisdom claims that creativity is a rich and complex phenomenon, made richer and more complex by the fact that we can talk about it in so many ways, technologically, culturally, socially and historically. Accordingly, most think it makes little sense to claim any computational theory to be a general theory of creativity. They would say, with great confidence, that a single generative mechanism, and a related mechanism for evaluating and filtering the outputs of generation, does not a general theory make, no matter how rich the outputs. They may cede that such theories could be a valuable contribution to the field, but likewise contend that computationalists must strive to synthesize the many different aspects of creativity, the many different modes of generation and evaluation, to arrive at a framework that will one day be considered general.

Of course others in the field do not hold these opinions, claiming that what was once perceived as amorphous has now crystallized into a comprehensive theory.

Stephen L. Thaler's work on a unified model of creativity

A unifying model of creativity[69] was proposed by S. L. Thaler through a series of international patents in computational creativity, beginning in 1997 with the issuance of U.S. Patent 5,659,666.[70] Based upon theoretical studies of traumatized neural networks and inspired by studies of damage-induced vibrational modes in simulated crystal lattices,[71] this extensive intellectual property suite taught the application of a broad range of noise, damage, and disordering effects to a trained neural network so as to drive the formation of novel or confabulatory patterns[72][73][74][75][76][77][78] that could potentially qualify as ideas and/or plans of action.

Thaler's scientific and philosophical papers both preceding and following the issuance of these patents described:

  1. The aspects of creativity accompanying a broad gamut of cognitive functions (e.g., waking to dreaming to near-death trauma),[79][80][81]
  2. A shorthand notation for describing creative neural architectures and their function,[82]
  3. Quantitative modeling of the rhythm with which creative cognition occurs,[69][83][84] and,
  4. A prescription for critical perturbation regimes leading to the most efficient generation of useful information by a creative neural system.[83][84][85]

Thaler has also recruited his generative neural architectures into a theory of consciousness that closely models the temporal evolution of thought, creative or not, while also accounting for the subjective feel associated with this hotly debated mental phenomenon.[69][83][86][87][88][89][84]

In 1989, in one of the most controversial reductions to practice of this general theory of creativity,[69] one neural net termed the "grim reaper," governed the synaptic damage (i.e., rule-changes) applied to another net that had learned a series of traditional Christmas carol lyrics. The former net, on the lookout for both novel and grammatical lyrics, seized upon the chilling sentence, "In the end all men go to good earth in one eternal silent night," thereafter ceasing the synaptic degradation process. In subsequent projects, these systems produced more useful results across many fields of human endeavor, oftentimes bootstrapping their learning from a blank slate based upon the success or failure of self-conceived concepts and strategies seeded upon such internal network damage.[90]


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

  • ICCC 2015, Park City, Utah, USA
  • ICCC 2014, Ljubljana, Slovenia
  • ICCC 2013, Sydney, Australia
  • ICCC 2012, Dublin, Ireland
  • ICCC 2011, Mexico City, Mexico
  • ICCC 2010, Lisbon, Portugal

Previously, the community of computational creativity has held a dedicated workshop, the International Joint Workshop on Computational Creativity, every year since 1999. Previous events in this series include:

  • 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, a stand-alone event
  • IJWCC 2008, Madrid, Spain, a stand-alone event

The steering committee for these events comprises the following researchers:

  • Oliver Bown, University of Sydney, Australia
  • Amílcar Cardoso, University of Coimbra, Portugal
  • Simon Colton, Goldsmiths, University of London, UK
  • Pablo Gervás, Universidad Complutense de Madrid, Spain
  • Nick Montfort, Massachusetts Institute of Technology, USA
  • Fraçoise Pachet, Sony CSL, France
  • Alison Pease, University of Dundee, UK
  • Rafael Pérez y Pérez, Autonomous Metropolitan University, México
  • Graeme Ritchie, University of Aberdeen, UK
  • Rob Saunders, University of Sydney, Australia
  • Hannu Toivonen, University of Helsinki, Finland
  • Dan Ventura, Brigham Young University, USA
  • Tony Veale, University College, Dublin, Eire

Publications and Forums

Design Computing and Cognition is one conference that addresses computational creativity. The ACM Creativity and Cognition conference is another forum for issues related to computational creativity.

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

  • Pereira, F. C. (2007). "Creativity and Artificial Intelligence: A Conceptual Blending Approach". Applications of Cognitive Linguistics series, Mouton de Gruyter.
  • Veale, T. (2012). "Exploding the Creativity Myth: The Computational Foundations of Linguistic Creativity". Bloomsbury Academic, London.
  • McCormack, J. and d'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". Mouton de Gruyter.

In addition to the proceedings of conferences and workshops, the computational creativity community has thus far produced three special journal issues dedicated to the topic:

  • 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 (forthcoming)

See also



  1. ^
  2. ^
  3. ^
  4. ^ Gibson, P. M. (1991) NEUROGEN, musical composition using genetic algorithms and cooperating neural networks, Second International Conference on Artificial Neural Networks: 309-313.
  5. ^ a b
  6. ^
  7. ^
  8. ^ Todd, P.M., and Loy, D.G. (Eds.) (1991). Music and connectionism. Cambridge, MA: MIT Press.
  9. ^ Todd, P.M. (1992). A connectionist system for exploring melody space. In Proceedings of the 1992 International Computer Music Conference (pp. 65-68). San Francisco: International Computer Music Association.
  10. ^ A dual backpropagation scheme for scalar-reward learning. P Munro - Ninth Annual Conference of the Cognitive Science, 1987
  11. ^ Neural networks for control and system identification. PJ Werbos - Decision and Control, 1989.
  12. ^ The truck backer-upper: An example of self-learning in neural networks. D Nguyen, B Widrow - IJCNN'89, 1989.
  13. ^ Forward models: Supervised learning with a distal teacher. MI Jordan, DE Rumelhart - Cognitive Science, 1992.
  14. ^ Marupaka, Nagendra, and Ali A. Minai. "Connectivity and creativity in semantic neural networks." Neural Networks (IJCNN), The 2011 International Joint Conference on. IEEE, 2011.
  15. ^
  16. ^
  17. ^ Thaler, S. L. (2011, " The Creativity Machine Paradigm: Withstanding the Argument from Consciousness,"
  18. ^
  19. ^
  20. ^
  21. ^
  22. ^
  23. ^
  24. ^ a b
  25. ^
  26. ^
  27. ^
  28. ^
  29. ^
  30. ^
  31. ^
  32. ^
  33. ^
  34. ^
  35. ^
  36. ^
  37. ^
  38. ^
  39. ^
  40. ^
  41. ^
  42. ^
  43. ^
  44. ^
  45. ^ David Cope (1987), "Experiments in Music Intelligence." In Proceedings of the International Computer Music Conference, San Francisco: Computer Music Assn.
  46. ^ Triumph of the Cyborg Composer
  47. ^ [1]
  48. ^
  49. ^
  50. ^
  51. ^ (French) Article de presse : « Génération automatique d'œuvres numériques », article sur l'invention Medal de Béatrice Perret du Cray », Science et Vie Micro
  52. ^
  53. ^
  54. ^ "Methods, systems and software for generating sentences, and visual and audio compositions representing said sentences" Canadian Patent 2704163
  55. ^
  56. ^
  57. ^ deepdream on GitHub
  58. ^
  59. ^
  60. ^
  61. ^
  62. ^
  63. ^
  64. ^
  65. ^
  66. ^
  67. ^
  68. ^ Schmidhuber, J. (1991), Curious model-building control systems. In Proc. ICANN, Singapore, volume 2, pp 1458-1463. IEEE.
  69. ^ a b c d Thaler, S. L. (2013) The Creativity Machine Paradigm, Encyclopedia of Creativity, Invention, Innovation, and Entrepreneurship, (ed.) E.G. Carayannis, Springer Science+Business Media, available at
  70. ^ Thaler, S.L., "Device for the autonomous generation of useful information,"
  71. ^ Thaler, S. L. (1982) "The Raman Spectrum of Neutron Irradiated Silicon," Ph.D. Thesis, University of Missouri, 1982
  72. ^ Thaler, S. L. (1997). "Device for the Autonomous Generation of Useful Information*: A Completely Connectionist Approach to Cognition, Creativity, and Machine Consciousness," International Conference on Vision, Recognition, Action, Neural Models of Mind and Machine, Boston University, May 28–31, 1997.
  73. ^ Confabulation (neural networks)
  74. ^ N. Marupaka, L. Lyer, A. Minai (2012). Connectivity and thought: The influence of semantic network structure in a neurodynamical model of thinking, Neural Networks (2012), doi:10.1016/j.neunet.2012.02.004, available at
  75. ^
  76. ^ Mayer, H. A. (2004). A modular neurocontroller for creative mobile autonomous robots learning by temporal difference, Systems, Man and Cybernetics, 2004 IEEE International Conference(Volume:6 )
  77. ^ Minati,G. and Vitiello, G. (2006) Mistakemaking machines,"inSyst.Emer.:Res.Develop.(Springer,NewYork),pp.67�68.
  78. ^ Roque, R. and Barreira, A. (2011). “O Paradigma da “Máquina de Criatividade” e a Geração de Novidades em um Espaço Conceitual,” 3º Seminário Interno de Cognição Artificial - SICA 2011 – FEEC – UNICAMP.
  79. ^ Thaler, S. L. (1993). "4-2-4 Encoder Death," World Congress on Neural Networks, WCNN'93
  80. ^
  81. ^
  82. ^ Thaler, S. L. (1996). "A Proposed Symbolism for Network-Implemented Discovery Processes," In Proceedings of the World Congress on Neural Networks, (WCNN’96), Lawrence Erlbaum, Mawah, NJ.
  83. ^ a b c Thaler, S. L. (1997) "A Quantitative Model of Seminal Cognition: The Creativity Machine Paradigm," Mind II Conference, Dublin Ireland.
  84. ^ a b c Thaler, S. L. (2014) "Synaptic Perturbation and Consciousness," International Journal of Machine Consciousness, Vol. 06, No. 02, pp. 75-107
  85. ^
  86. ^ Thaler, S. L. (1996) "Network 'cavitation' in the modeling of consciousness," Toward a Science of Consciousness, Tucson, AZ, March, 1996.
  87. ^ Thaler, S. L. (1996) "Is Neuronal Chaos the Source of Stream of Consciousness?", World Congress on Neural Networks, San Diego, 1996.
  88. ^ Thaler, S. L. (2010) "Thalamocortical Algorithms in Space! The Building of Conscious Machines and the Lessons Thereof," Proceedings of the World Future Society, 2010
  89. ^ Thaler, S. L. (2011), "The Creativity Machine: Withstanding the Argument from Consciousness," APA Newsletter on Philosophy and Computers
  90. ^ for example, US Patent 7,454,388

External links

Further reading
  • An Overview of Artificial Creativity on Think Artificial
  • Cohen, H., "the further exploits of AARON, Painter", SEHR, volume 4, issue 2: Constructions of the Mind, 1995
  • Artificial Creativity Blog
  • Gero, J. S. and Sosa, R. "Artificial Creativity in Communities of Design Agents", 2006
  • Máquinas de computación, creatividad artificial y cine digital
  • LaDuke, B. "Knowledge Machine"
  • Plotkin, R. "The Genie in the Machine"
  • Cohen, A. M. (2009) "Stephen Thaler’s Imagination Machines"


  • Noorderlicht: Margaret Boden and Stephen Thaler on Creative Computers
  • In Its Image