abstract: For the past three decades, the design of an effective strategy for generating poetry that matches that of a human’s creative capabilities and complexities has been an elusive goal in artificial intelligence (AI) and natural language generation (NLG) research, and among linguistic creativity researchers in particular. This thesis presents a novel approach to fixed verse poetry generation using neural word embeddings. During the course of generation, a two layered poetry classifier is developed. The first layer uses a lexicon based method to classify poems into types based on form and structure, and the second layer uses a supervised classification method to classify poems into subtypes based on content with an accuracy of 92%. The system then uses a two-layer neural network to generate poetry based on word similarities and word movements in a 50-dimensional vector space. The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators. / Dissertation/Thesis / Masters Thesis Computer Science 2016

The sound synthesizer is an electronic musical instrument that has become commonplace in audio production for music, film, television and video games. Despite its widespread use, creating new sounds on a synthesizer - referred to as synthesizer programming - is a complex task that can impede the creative process. The primary aim of this thesis is to support the development of techniques to assist synthesizer users to more easily achieve their creative goals. One of the main focuses is the development and evaluation of algorithms for inverse synthesis, a technique that involves the prediction of synthesizer parameters to match a target sound. Deep learning and evolutionary programming techniques are compared on a baseline FM synthesis problem and a novel hybrid approach is presented that produces high quality results in less than half the computation time of a state-of-the-art genetic algorithm. Another focus is the development of intuitive user interfaces that encourage novice users to engage with synthesizers and learn the relationship between synthesizer parameters and the associated auditory result. To this end, a novel interface (Synth Explorer) is introduced that uses a visual representation of synthesizer sounds on a two-dimensional layout. An additional focus of this thesis is to support further research in automatic synthesizer programming. An open-source library (SpiegeLib) has been developed to support reproducibility, sharing, and evaluation of techniques for inverse synthesis. Additionally, a large-scale dataset of one billion sounds paired with synthesizer parameters (synth1B1) and a GPU-enabled modular synthesizer (torchsynth) are also introduced to support further exploration of the complex relationship between synthesizer parameters and auditory results. / Graduate

Computational creativity seeks, in part, to develop autonomous agents that exhibit creativity. Language is an ideal creative domain for studying computer agents due to its rich interconnectedness and immense space of possible combinations. This dissertation explores the design, testing, and theory of creative computer systems that write microfiction and play the board game Codenames. The designs of these systems are all similarly based on building up creative artifacts from the underlying structure of the relationships between words. A critical component of the creative process is the ability to evaluate the quality of creative output. Human and automated assessment of our creative systems' outputs yields insights into the challenge of automated creative evaluation. Those insights are formalized into a novel paradigm for designing creative systems and theoretical analyses of the properties of creative domains that facilitate evaluation.

This paper presents the cooperative modelling methodology used in the Information Society foresight carried out within the research project SCETIST. The class of models here presented used the concept of group decision creativity that has been elaborated for the use in a Living Lab. The trends and scenarios are discussed and refined during cooperative activities, finally verified using the simulation of a hybrid system consisting of qualitative information processing, and a discretetime- control system with a discrete-event component.

This paper presents the cooperative modelling methodology used in the Information Society foresight carried out within the research project SCETIST. The class of models here presented used the concept of group decision creativity that has been elaborated for the use in a Living Lab. The trends and scenarios are discussed and refined during cooperative activities, finally verified using the simulation of a hybrid system consisting of qualitative information processing, and a discretetime- control system with a discrete-event component.

While it is important for systems intended to enhance musical creativity to define and explore musical ideas conceived by individual users, many limit musical freedom by focusing on maintaining musical structure, thereby impeding the user's freedom to explore his or her individual style. This dissertation presents a comprehensive body of work that introduces a new musical representation that allows users to explore a space of musical rules that are created from their own melodies. This representation, called functional scaffolding for musical composition (FSMC), exploits a simple yet powerful property of multipart compositions: The pattern of notes and rhythms in different instrumental parts of the same song are functionally related. That is, in principle, one part can be expressed as a function of another. Music in FSMC is represented accordingly as a functional relationship between an existing human composition, or scaffold, and an additional generated voice. This relationship is encoded by a type of artificial neural network called a compositional pattern producing network (CPPN). A human user without any musical expertise can then explore how these additional generated voices should relate to the scaffold through an interactive evolutionary process akin to animal breeding. The utility of this insight is validated by two implementations of FSMC called NEAT Drummer and MaestroGenesis, that respectively help users tailor drum patterns and complete multipart arrangements from as little as a single original monophonic track. The five major contributions of this work address the overarching hypothesis in this dissertation that functional relationships alone, rather than specialized music theory, are sufficient for generating plausible additional voices. First, to validate FSMC and determine whether plausible generated voices result from the human-composed scaffold or intrinsic properties of the CPPN, drum patterns are created with NEAT Drummer to accompany several different polyphonic pieces. Extending the FSMC approach to generate pitched voices, the second contribution reinforces the importance of functional transformations through quality assessments that indicate that some partially FSMC-generated pieces are indistinguishable from those that are fully human. While the third contribution focuses on constructing and exploring a space of plausible voices with MaestroGenesis, the fourth presents results from a two-year study where students discuss their creative experience with the program. Finally, the fifth contribution is a plugin for MaestroGenesis called MaestroGenesis Voice (MG-V) that provides users a more natural way to incorporate MaestroGenesis in their creative endeavors by allowing scaffold creation through the human voice. Together, the chapters in this dissertation constitute a comprehensive approach to assisted music generation, enabling creativity without the need for musical expertise.

En 2016, un « nouveau Rembrandt » a été créé par intelligence artificielle dans le cadre du projet The Next Rembrandt. Grâce à la méthode d’apprentissage profond, un ordinateur a en effet permis la réalisation d’un tableau qui, selon les experts, aurait pu être créé par le maître hollandais. Ainsi, une création artistique a été conçue avec un programme d’intelligence artificielle, « en collaboration » avec des humains. Depuis, de nouvelles créations algorithmiques ont vu le jour, en minimisant chaque fois davantage l’empreinte créatrice humaine. Mais comment le droit d’auteur canadien encadre-t-il ou, le cas échéant, pourrait-il encadrer ce type de créations ? Voici la question générale à laquelle notre projet de recherche souhaite répondre. En dépit des récentes avancées technologiques et d’un certain abus de langage, l’intelligence artificielle n’est pas (encore) entièrement autonome (Chapitre liminaire). Il en résulte qu’un humain crée les dessous de l’œuvre, c’est-à-dire les règles dans le cadre duquel les créations sont produites. À l’heure actuelle, les créations « artificielles » sont donc issues d’un processus où l’algorithme agit comme simple outil. Partant, les principes classiques de droit d’auteur doivent s’appliquer à ces créations assistées par intelligence artificielle (Chapitre premier). En l’espèce, les critères d’originalité et d’autorat constituent les principaux obstacles à la protection de (certaines) créations algorithmiques. En outre, le processus collaboratif de création ne permet pas d’identifier systématiquement des co-auteurs faisant preuve « de talent et de jugement » (Chapitre deux). Dans ce contexte singulier, des juristes étrangers ont proposé des « solutions », afin de protéger les créations produites « artificiellement » par leurs régimes de droit d’auteur respectifs (Chapitre trois). La réception des propositions étrangères en sol canadien n’est toutefois pas souhaitable, car elle risque de fragiliser la cohérence interne de la Loi, ainsi que les fondements du régime. Dès lors, ces solutions ne permettent pas de résoudre la « problématique » des créations algorithmiques. Quelle devrait donc être la réponse canadienne ? Il s’agit de la question à laquelle nous répondons au Chapitre quatre. Afin de respecter l’intégrité du régime de droit d’auteur canadien, nous concluons que seules les créations répondant aux critères de la législation canadienne sur le droit d’auteur doivent être protégées. Les productions ne parvenant pas à respecter l’une ou l’autre des conditions de protection tomberaient, pour leur part, dans le domaine public. En dépit de ce constat, nous croyons que la constitution d’un régime sui generis, propre aux créations algorithmiques, pourrait être appropriée. Il appartiendra cependant au gouvernement canadien de décider si l’édification d’un tel régime est pertinente. Pour ce faire, il sera nécessaire d’obtenir des données probantes de la part des différentes parties prenantes. Il s’agit-là du dilemme auquel le Canada fait face. / In 2016, a « new Rembrandt » was created with artificial intelligence as part of The Next Rembrandt project. Thanks to the deep learning method, a computer has indeed made it possible to make a painting that, according to experts, could have been created by the Dutch Master. Thus, an artistic creation was designed with an artificial intelligence program, « in collaboration » with humans. Since then, new algorithmic creations have emerged, each time further minimizing the human creative footprint. But how does or could the Canadian copyright regime protect this type of creation ? This is the general question that our research project wishes to answer. Despite recent technological advances and a certain abuse of language, artificial intelligence is not (yet) autonomous (Preliminary Chapter). As a result, a human creates the underside of the work, that is, the rules within which the creations are produced. At present, « artificial » creations are therefore the result of a process where the algorithm acts as a simple tool. Therefore, the classical principles of copyright should apply to such creations produced with computer assistance (Chapter One). In the present case, the conditions of originality and authorship constitute the main obstacles to the protection of (certain) algorithmic creations. In addition, the collaborative creative process does not systematically allow the identification of coauthors (Chapter Two). In this singular context, foreign authors have proposed solutions to protect these creations by their respective copyright regimes (Chapter Three). However, the adoption of these proposals in Canada is not desirable, as it may weaken the internal scheme of the Canadian copyright regime, as well as its foundations. As such, these solutions do not solve the « problem » of algorithmic 5 creations. What should be the Canadian response ? This is the question we answer in Chapter Four. In order to protect the integrity of the Canadian copyright regime, we conclude that only creations that meet the criteria of the Copyright Act should be protected. Productions that fail to comply with any of these conditions should fall into the public domain. Despite this observation, we believe that the constitution of a sui generis regime specific to algorithmic creations could be appropriate. Yet, it will be up to the Canadian government to decide whether the creation of such a regime is pertinent. This will require gathering evidence from different stakeholders. This is the dilemma that Canada is facing.