Computational creativity has been called the "final frontier" of artificial intelligence due to the difficulty inherent in defining and implementing creativity in computational systems. Despite this difficulty computer creativity is becoming a more significant part of our everyday lives, in particular music. This is observed in the prevalence of music recommendation systems, co-creational music software packages, smart playlists, and procedurally-generated video games. Significant progress can be seen in the advances in industrial applications such as Spotify, Pandora, Apple Music, etc., but several problems persist. Of more general interest, however, is the question of whether or not computers can exhibit autonomous creativity in music composition. One of the primary challenges in this endeavor is enabling computational systems to create music that exhibits global structure, that can learn structure from data, and which can effectively incorporate autonomy and intention. We seek to address these challenges in the context of a modular machine learning framework called hierarchical Bayesian program learning (HBPL). Breaking the problem of music composition into smaller pieces, we focus primarily on developing machine learning models that solve the problems related to structure. In particular we present an adaptation of non-homogenous Markov models that enable binary constraints and we present a structural learning model, the multiple Smith-Waterman (mSW) alignment method, which extends sequence alignment techniques from bioinformatics. To address the issue of intention, we incorporate our work on structured sequence generation into a full-fledged computational creative system called Pop* which we show through various evaluative means to possess to varying extents the characteristics of creativity and also creativity itself.

No description available.

Developing advanced semantic models is important in building computational systems that can not only understand language but also convey ideas and concepts to others. Semantic models can allow a creative image-producing-agent to autonomously produce artifacts that communicate an intended meaning. This notion of communicating meaning through art is often considered a necessary part of eliciting an aesthetic experience in the viewer and can thus enhance the (perceived) creativity of the agent. Computational creativity, a subfield of artificial intelligence, deals with designing computational systems and algorithms that either automatically create original and functional products, or that augment the ability of humans to do so. We present work on DARCI (Digital ARtist Communicating Intention), a system designed to autonomously produce original images that convey meaning. In order for DARCI to automatically express meaning through the art it creates, it must have its own semantic model that is perceptually grounded with visual capabilities.The work presented here focuses on designing, building, and incorporating advanced semantic and perceptual models into the DARCI system. These semantic models give DARCI a better understanding of the world and enable it to be more autonomous, to better evaluate its own artifacts, and to create artifacts with intention. Through designing, implementing, and studying DARCI, we have developed evaluation methods, models, frameworks, and theories related to the creative process that can be generalized to other domains outside of visual art. Our work on DARCI has even influenced the visual art community through several collaborative efforts, art galleries, and exhibits. We show that the DARCI system is successful at autonomously producing original art that is meaningful to human viewers. We also discuss insights that our efforts have contributed to the field of computational creativity.

Narrative Intelligence is the ability to craft, tell, understand, and respond appropriately to narratives. It has been proposed as a vital component of machines aiming to understand human activities or to communicate effectively with humans. However, most existing systems purported to demonstrate Narrative Intelligence rely on manually authored knowledge structures that require extensive expert labor. These systems are constrained to operate in a few domains where knowledge has been provided. This dissertation investigates the learning of knowledge structures to support Narrative Intelligence in any domain. I propose and build a system that, from an corpus of simple exemplar stories, learns complex knowledge structures that subsequently enable the creation, telling, and understanding of narratives. The knowledge representation balances the complexity of learning and the richness of narrative applications, so that we can (1) learn the knowledge robustly in the presence of noise, (2) generate a large variety of highly coherent stories, (3) tell them in recognizably different narration styles and (4) understand stories efficiently. The accuracy and effectiveness of the system have been verified by a series of user studies and computational experiments. As a result, the system is able to demonstrate Narrative Intelligence in any domain where we can collect a small number of exemplar stories. This dissertation is the first step toward scaling computational narrative intelligence to meet the challenges of the real world.

A presente tese de doutorado descreve uma pesquisa interdisciplinar nas áreas de criatividade computacional e agentes cognitivos. A motivação para a integração dessas áreas é o estudo da habilidade humana de utilizar suas experiências prévias e conhecimento geral para resolver problemas e lidar com situações a partir do momento em que as mesmas são apresentadas. Imbuídos dessa motivação, nosso propósito é ampliar a utilização do conhecimento de agentes, inspirado na forma como, nós, humanos entendemos e vivenciamos o mundo. Nossa abordagem para concretizar essa visão de pesquisa é adotar teorias e resultados das ciências cognitivas e neurociências como fundamentação para um modelo computacional de agentes capazes de atuar criativamente. Assim sendo, adotamos a teoria do concept blending (fusão conceitual – tradução do autor) (FAUCONNIER; TURNER, 1998), advinda da lingüística cognitiva e teoria da mente como a fundação de nosso modelo. O modelo de agentes criativos proposto integra uma implementação da fusão conceitual em uma estrutura BDI. Concretamente, utilizamos a implementação da linguagem AgentSpeak fornecida pelo framework Jason, para manipular o raciocínio teórico (crenças) e prático (desejos, planos e intenções) do agente. Logo, o objeto principal de estudo desta tese é a utilização da fusão conceitual em uma estrutura de agentes inteligentes visando contribuições em criatividade computacional e agentes. Considerando a área da criatividade computacional, especificamos um modelo da fusão conceitual que define explicitamente as regras necessárias para representar uma tipologia da fusão. Ademais, a integração de uma estrutura de agentes BDI ao modelo possibilita a construção automatizada das entradas e de informações de domínio para utilizar o processo de fusão. Focando na área de agentes, nossa contribuição é caracterizada pela aplicação do processo de raciocínio criativo para fornecer alternativas de uso do conhecimento prático e teórico. Dada a especificação da fusão aqui apresentada, é possível integrar diferentes estratégias de adaptação para lidar com a falha de intenções ou outras situações que requerem adaptação. Outra funcionalidade é a capacidade de utilizar diferentes representações de conhecimento, assumindo a disponibilidade de uma definição descritiva (na linguagem OWL) da representação. O modelo de fusão conceitual também é aplicado na modelagem do raciocínio de um sistema de recomendação educacional. Finalmente, nosso modelo de fusão representa um trabalho inicial em direção a um modelo cognitivo no qual fusão, agência e outras funções cognitivas (e.g. aprendizagem) interagem para simular diferentes funcionalidades do pensamento humano. / This PhD thesis describes an interdisciplinary research on computational creativity and cognitive agents. Our motivation to integrate these two areas is to study the human skill that uses previous experiences and knowledge to solve unpredicted problems and situations. Imbued by that motivation, our purpose is to improve the applicability of the agent’s knowledge, inspired in the way that we humans understand and experience the world. Our approach towards that research view is to adopt theories and results from cognitive and neural sciences as the grounding to a computational model of agents capable of acting creatively. Thus, we adopt the concept blending theory (FAUCONNIER; TURNER, 1998) – that originated from cognitive linguistics and theory of the mind – as the grounding of our model. Therefore, our proposal of creative agents integrates an implementation of concept blending into a BDI structure. In concrete terms, we use Jason’s implementation of AgentSpeak to manipulate the agent’s theoretical (beliefs) and practical (desires and intentions) reasoning. Hence, the main topic of study of this research is the utilization of concept blending in a structure of intelligent agents. Consequently, we observe our contributions under two perspectives. Regarding computational creativity, we specify a model for concept blending that explicitly defines rules to represent a blending typology. Furthermore, integrating a BDI structure to the model allows the automated construction of inputs and domain information to feed the blending process. Focusing on agents, our contribution is on the process of creative reasoning applied to supply alternative ways to use practical and theoretical knowledge. Given the blending specification defined here, it is possible to integrate different adaptation strategies to handle intention failure or other adaptation scenarios. Another feature is the possibility to work with different knowledge representations given its descriptive logics (using the OWL language) definition. The blending specification is also applied to model the reasoning of an educational recommender system. Finally, the defined model represents an initial work towards a cognition model where blending, agency and other cognitive operations (e.g. learning) interact together to simulate different features of the human thinking.

A presente tese de doutorado descreve uma pesquisa interdisciplinar nas áreas de criatividade computacional e agentes cognitivos. A motivação para a integração dessas áreas é o estudo da habilidade humana de utilizar suas experiências prévias e conhecimento geral para resolver problemas e lidar com situações a partir do momento em que as mesmas são apresentadas. Imbuídos dessa motivação, nosso propósito é ampliar a utilização do conhecimento de agentes, inspirado na forma como, nós, humanos entendemos e vivenciamos o mundo. Nossa abordagem para concretizar essa visão de pesquisa é adotar teorias e resultados das ciências cognitivas e neurociências como fundamentação para um modelo computacional de agentes capazes de atuar criativamente. Assim sendo, adotamos a teoria do concept blending (fusão conceitual – tradução do autor) (FAUCONNIER; TURNER, 1998), advinda da lingüística cognitiva e teoria da mente como a fundação de nosso modelo. O modelo de agentes criativos proposto integra uma implementação da fusão conceitual em uma estrutura BDI. Concretamente, utilizamos a implementação da linguagem AgentSpeak fornecida pelo framework Jason, para manipular o raciocínio teórico (crenças) e prático (desejos, planos e intenções) do agente. Logo, o objeto principal de estudo desta tese é a utilização da fusão conceitual em uma estrutura de agentes inteligentes visando contribuições em criatividade computacional e agentes. Considerando a área da criatividade computacional, especificamos um modelo da fusão conceitual que define explicitamente as regras necessárias para representar uma tipologia da fusão. Ademais, a integração de uma estrutura de agentes BDI ao modelo possibilita a construção automatizada das entradas e de informações de domínio para utilizar o processo de fusão. Focando na área de agentes, nossa contribuição é caracterizada pela aplicação do processo de raciocínio criativo para fornecer alternativas de uso do conhecimento prático e teórico. Dada a especificação da fusão aqui apresentada, é possível integrar diferentes estratégias de adaptação para lidar com a falha de intenções ou outras situações que requerem adaptação. Outra funcionalidade é a capacidade de utilizar diferentes representações de conhecimento, assumindo a disponibilidade de uma definição descritiva (na linguagem OWL) da representação. O modelo de fusão conceitual também é aplicado na modelagem do raciocínio de um sistema de recomendação educacional. Finalmente, nosso modelo de fusão representa um trabalho inicial em direção a um modelo cognitivo no qual fusão, agência e outras funções cognitivas (e.g. aprendizagem) interagem para simular diferentes funcionalidades do pensamento humano. / This PhD thesis describes an interdisciplinary research on computational creativity and cognitive agents. Our motivation to integrate these two areas is to study the human skill that uses previous experiences and knowledge to solve unpredicted problems and situations. Imbued by that motivation, our purpose is to improve the applicability of the agent’s knowledge, inspired in the way that we humans understand and experience the world. Our approach towards that research view is to adopt theories and results from cognitive and neural sciences as the grounding to a computational model of agents capable of acting creatively. Thus, we adopt the concept blending theory (FAUCONNIER; TURNER, 1998) – that originated from cognitive linguistics and theory of the mind – as the grounding of our model. Therefore, our proposal of creative agents integrates an implementation of concept blending into a BDI structure. In concrete terms, we use Jason’s implementation of AgentSpeak to manipulate the agent’s theoretical (beliefs) and practical (desires and intentions) reasoning. Hence, the main topic of study of this research is the utilization of concept blending in a structure of intelligent agents. Consequently, we observe our contributions under two perspectives. Regarding computational creativity, we specify a model for concept blending that explicitly defines rules to represent a blending typology. Furthermore, integrating a BDI structure to the model allows the automated construction of inputs and domain information to feed the blending process. Focusing on agents, our contribution is on the process of creative reasoning applied to supply alternative ways to use practical and theoretical knowledge. Given the blending specification defined here, it is possible to integrate different adaptation strategies to handle intention failure or other adaptation scenarios. Another feature is the possibility to work with different knowledge representations given its descriptive logics (using the OWL language) definition. The blending specification is also applied to model the reasoning of an educational recommender system. Finally, the defined model represents an initial work towards a cognition model where blending, agency and other cognitive operations (e.g. learning) interact together to simulate different features of the human thinking.

A presente tese de doutorado descreve uma pesquisa interdisciplinar nas áreas de criatividade computacional e agentes cognitivos. A motivação para a integração dessas áreas é o estudo da habilidade humana de utilizar suas experiências prévias e conhecimento geral para resolver problemas e lidar com situações a partir do momento em que as mesmas são apresentadas. Imbuídos dessa motivação, nosso propósito é ampliar a utilização do conhecimento de agentes, inspirado na forma como, nós, humanos entendemos e vivenciamos o mundo. Nossa abordagem para concretizar essa visão de pesquisa é adotar teorias e resultados das ciências cognitivas e neurociências como fundamentação para um modelo computacional de agentes capazes de atuar criativamente. Assim sendo, adotamos a teoria do concept blending (fusão conceitual – tradução do autor) (FAUCONNIER; TURNER, 1998), advinda da lingüística cognitiva e teoria da mente como a fundação de nosso modelo. O modelo de agentes criativos proposto integra uma implementação da fusão conceitual em uma estrutura BDI. Concretamente, utilizamos a implementação da linguagem AgentSpeak fornecida pelo framework Jason, para manipular o raciocínio teórico (crenças) e prático (desejos, planos e intenções) do agente. Logo, o objeto principal de estudo desta tese é a utilização da fusão conceitual em uma estrutura de agentes inteligentes visando contribuições em criatividade computacional e agentes. Considerando a área da criatividade computacional, especificamos um modelo da fusão conceitual que define explicitamente as regras necessárias para representar uma tipologia da fusão. Ademais, a integração de uma estrutura de agentes BDI ao modelo possibilita a construção automatizada das entradas e de informações de domínio para utilizar o processo de fusão. Focando na área de agentes, nossa contribuição é caracterizada pela aplicação do processo de raciocínio criativo para fornecer alternativas de uso do conhecimento prático e teórico. Dada a especificação da fusão aqui apresentada, é possível integrar diferentes estratégias de adaptação para lidar com a falha de intenções ou outras situações que requerem adaptação. Outra funcionalidade é a capacidade de utilizar diferentes representações de conhecimento, assumindo a disponibilidade de uma definição descritiva (na linguagem OWL) da representação. O modelo de fusão conceitual também é aplicado na modelagem do raciocínio de um sistema de recomendação educacional. Finalmente, nosso modelo de fusão representa um trabalho inicial em direção a um modelo cognitivo no qual fusão, agência e outras funções cognitivas (e.g. aprendizagem) interagem para simular diferentes funcionalidades do pensamento humano. / This PhD thesis describes an interdisciplinary research on computational creativity and cognitive agents. Our motivation to integrate these two areas is to study the human skill that uses previous experiences and knowledge to solve unpredicted problems and situations. Imbued by that motivation, our purpose is to improve the applicability of the agent’s knowledge, inspired in the way that we humans understand and experience the world. Our approach towards that research view is to adopt theories and results from cognitive and neural sciences as the grounding to a computational model of agents capable of acting creatively. Thus, we adopt the concept blending theory (FAUCONNIER; TURNER, 1998) – that originated from cognitive linguistics and theory of the mind – as the grounding of our model. Therefore, our proposal of creative agents integrates an implementation of concept blending into a BDI structure. In concrete terms, we use Jason’s implementation of AgentSpeak to manipulate the agent’s theoretical (beliefs) and practical (desires and intentions) reasoning. Hence, the main topic of study of this research is the utilization of concept blending in a structure of intelligent agents. Consequently, we observe our contributions under two perspectives. Regarding computational creativity, we specify a model for concept blending that explicitly defines rules to represent a blending typology. Furthermore, integrating a BDI structure to the model allows the automated construction of inputs and domain information to feed the blending process. Focusing on agents, our contribution is on the process of creative reasoning applied to supply alternative ways to use practical and theoretical knowledge. Given the blending specification defined here, it is possible to integrate different adaptation strategies to handle intention failure or other adaptation scenarios. Another feature is the possibility to work with different knowledge representations given its descriptive logics (using the OWL language) definition. The blending specification is also applied to model the reasoning of an educational recommender system. Finally, the defined model represents an initial work towards a cognition model where blending, agency and other cognitive operations (e.g. learning) interact together to simulate different features of the human thinking.

Computational creativity is a new and developing field of artificial intelligence concerned with computational systems that either autonomously produce original and functional products, or that augment the ability of humans to do so. As the role of computers in our daily lives is continuing to expand, the need for such systems is becoming increasingly important. We introduce and document the development of a new “creative” system, called DARCI (Digital ARtist Communicating Intention), that is designed to autonomously create novel artistic images that convey linguistic concepts to the viewer. Within the scope of this work, the system becomes capable of creating non-photorealistic renderings of existing image compositions so that they convey the semantics of given adjectives. Ultimately, we show that DARCI is capable of producing surprising artifacts that are competitive, in some ways, with those produced by human artists. As with the development of any “creative” system, we are faced with the challenges of incorporating the philosophies of creativity into the design of the system, assessing the system's creativity, overcoming technical shortcomings of extant modern algorithms, and justifying the system within its creative domain (in this case, visual art). In meeting these challenges with DARCI, we demonstrate three broad contributions of the system: 1) the contribution to the field of computational creativity in the form of an original system, new approaches to achieving autonomy in creative systems, and new practical assessment methods; 2) the contribution to the field of computer vision in the form of new image features for affective image annotation and a new dataset; and 3) the contribution to the domain of visual art in the form of mutually beneficial collaborations and participation in several art galleries and exhibits.

Music and emotion are two realms traditionally considered to be unique to human intelligence. This dissertation focuses on furthering artificial intelligence research, specifically in the area of computational creativity, by investigating methods of composing music that elicits desired emotional and physiological responses. It includes the following: an algorithm for generating original musical selections that effectively elicit targeted emotional and physiological responses; a description of some of the musical features that contribute to the conveyance of a given emotion or the elicitation of a given physiological response; and an account of how this algorithm can be used effectively in two different situations, the generation of soundtracks for fairy tales and the generation of melodic accompaniments for lyrics. This dissertation also presents research on more general machine learning topics. These include a method of combining output from base classifiers in an ensemble that improves accuracy over a number of different baseline strategies and a description of some of the problems inherent in the Bayesian model averaging strategy and a novel algorithm for improving it.

In this dissertation, I present Dramatis, a computational human behavior model of suspense based on Gerrig and Bernardo's de nition of suspense. In this model, readers traverse a search space on behalf of the protagonist, searching for an escape from some oncoming negative outcome. As the quality or quantity of escapes available to the protagonist decreases, the level of suspense felt by the audience increases. The major components of Dramatis are a model of reader salience, used to determine what elements of the story are foregrounded in the reader's mind, and an algorithm for determining the escape plan that a reader would perceive to be the most likely to succeed for the protagonist. I evaluate my model by comparing its ratings of suspense to the self-reported suspense ratings of human readers. Additionally, I demonstrate that the components of the suspense model are sufficient to produce these human-comparable ratings.