Those few AI models of creativity that do rely on novel combinations generally combine random choice with specific criteria chosen for the task at hand. For example, a joke-generating programme called JAPE churns out riddles like these:. JAPE is really doing exploratory creativity. It has structured templates for eight types of joke, and explores the possibilities with fairly acceptable results. Exploratory creativity in general is easier to model in computers than combinational creativity is.
In JAPE, the style is the joke template. All these, and more, have been achieved already. Many people assume that transformational creativity is the most difficult of all for computer modelling — perhaps even impossible.
After all, a computer can do only what its programme tells it to do. So how can there be any transformation? There can be, if the programme can alter its own rules. Such programs exist, and are used not only in some computer art but also in designing engines. Some evolutionary programmes can also prune the results, selecting those which are closest to what the task requires, and using them to breed the next generation. The key problem again is relevance, or value. Human minds are far too rich, far too subtle, and far too idiosyncratic for that. By Margaret Boden. Saad Faruque. Share to Facebook.
Tweet This. Share via Email. Artificial Intelligence. People can be imaginative, but can we ever hope to make an artificial intelligence that truly is? The Institute of Art and Ideas August 15th Keep up.
Artificial Intelligence | Can Computers Be Creative?
Nightmare Fuel. The jazz style in particular abounds with programs that create improvisations of a reasonable level. However, no approach so far exhibits virtuoso-level performance. We describe an architecture for the generation of virtuoso bebop phrases which integrates novel music generation mechanisms in a principled way.
We argue that modelling such outstanding phenomena can contribute substantially to the understanding of creativity in humans and machines. A Live Algorithm is an autonomous machine that interacts with musicians in an improvised setting. This chapter outlines perspectives on Live Algorithm research, offering a high level view for the general reader, as well as more detailed and specialist analysis. Some of the most important issues from these fields are considered.
A modular decomposition and an associated set of wiring diagrams is offered as a practical and conceptual tool. Technical, behavioural, social and cultural contexts are considered, and some signposts for future Live Algorithm research are suggested. This chapter focuses on interactive tools for musical composition which, through computational means, have some degree of autonomy in the creative process. This can engender two distinct benefits: extending our practice through new capabilities or trajectories, and reflecting our existing behaviour, thereby disrupting habits or tropes that are acquired over time.
We examine these human-computer partnerships from a number of perspectives, providing a series of taxonomies based on a systems behavioural properties, and discuss the benefits and risks that such creative interactions can provoke. In this chapter, I propose a model of an artistic creative process, based on study of my own creative processes over twenty years of activities as composer and improviser. The model describes the creative process as a structured exploration of the space of the possible, emphasising the interplay between a dynamic concept and the changing material form of the work.
Combining ideas, tools, material and memory, creativity is described as a coherent, dynamic, and iterative process that navigates the space of the chosen medium, guided by the tools at hand, and by the continuously revised ideas, significantly extending previous spatial models of creativity. This involves repeated misinterpretation and coincidences, which are crucial in human creative processes, adding meaning and depth to the artwork. A few examples from real life are given as illustrations of the model, together with a discussion of phenomena such as appreciation, skill and collaborative creativity.
Computer programming is central to the digital arts, and is a comparatively new creative activity. We take an anthropocentric view of computer programming in the arts, examining how the creative process has been extended to include the authorship and execution of algorithms. The role of human perception in this process is a focus, contrasted and ultimately combined with a more usual linguistic view of programming.
Practical impacts on the notation of programs in the arts are highlighted, both in terms of space and time, marking out this new domain for programming language design. Human creativity typically includes a self-critical aspect that guides innovation towards a productive end. This chapter offers a brief history of, and outlook for, computational aesthetic evaluation by digital systems as a contribution towards potential machine creativity.
First, computational aesthetic evaluation is defined and the difficult nature of the problem is outlined.
- Politics and Fate (Themes for the 21st Century)?
- Bible Stories for Children With Modern Lessons: Jonah and the Big Fish.
- Burning Lust (BBW Romance Erotica – Firefighter Alpha Males).
- My Tumor Makes Me Giggle.
Next, a brief history of computational aesthetic evaluation is offered, including the use of formulaic and geometric theories; design principles; evolutionary systems including extensions such as coevolution, niche construction, agent swarm behaviour and curiosity; artificial neural networks and connectionist models; and complexity models. Following this historical review, a number of possible contributions towards future computational aesthetic evaluation methods are noted. Included are insights from evolutionary psychology; models of human aesthetics from psychologists such as Arnheim, Berlyne, and Martindale; a quick look at empirical studies of human aesthetics; the nascent field of neuroaesthetics; new connectionist computing models such as hierarchical temporal memory; and computer architectures for evolvable hardware.
Finally, it is suggested that the effective complexity paradigm is more useful than information or algorithmic complexity when thinking about aesthetics. The ability of human or artificial agents to evaluate their works, as well as the works of others, is an important aspect of creative behaviour, possibly even a requirement.
- Cami and Friends Present Bathing in the Sun - SweetNatureNudes Issue #106.
- Association for Computational Creativity.
- Messerschmitts Over America-Part 7.
- Price of a Tattooed Soul.
- Computers and Creativity.
- The Everyday Negotiator: 50 Practical Tactics for Work and Life?
In artistic fields such as visual arts and music, this evaluation capacity relies, at least partially, on aesthetic judgement. This chapter analyses issues regarding the development of computational systems that perform aesthetic judgements focusing on their validation. An adaptive system is presented and its performance assessed using the above-mentioned validation methodologies.
The learning progress of the encoder is the intrinsic reward for the reward optimiser. That is, the latter is motivated to invent interesting spatio-temporal patterns that the encoder does not yet know but can easily learn to encode better with little computational effort. To maximise expected reward in the absence of external reward , the reward optimiser will create more and more-complex behaviours that yield temporarily surprising but eventually boring patterns that make the encoder quickly improve.
I have argued that this simple principle explains science, art, music and humour. It is possible to rigorously formalise it and implement it on learning machines, thus building artificial robotic scientists and artists equipped with curiosity and creativity. I summarise my work on this topic since , and present a previously unpublished low-complexity artwork computable by a very short program discovered through active search for novel patterns according to the principles of the theory.
This chapter introduces a new definition of creativity that is independent of notions of value or appropriateness. These notions, we argue, have encumbered previous definitions and confused the production of software-based creativity. Our definition defines the creativity of a generative procedure by reference to its ability to create artefacts that are improbable with respect to those generated using previous methods. We discuss the implications of our new definition, in particular by exploring its application to human endeavour and to biological processes including evolution.
The chapter also outlines some objections to our definition that we believe may arise, and we put our rebuttals to these. Finally, we summarise the practical implementation of our definition in the context of image generation software. Computational creativity is not limited to the study of human-like creativity and forces us to think about creativity as a general process that can be applied wherever new things come into existence. In this chapter I propose that in order to unify various forms of creativity it is necessary to consider a distinction between two types of creativity: generative creativity, in which things are created as the result of a process regardless of their value, and adaptive creativity, in which things are created as adaptive responses by a system to its situation.
Whilst individual human creativity is typically of the adaptive form, collectively humans are engaged in processes of generative creativity as well as adaptive creativity. It is helpful to understand human creative behaviour as part of a social process involving these two aspects, and this is relevant to understanding how manmade artefacts can act as creative agents in social networks.
Creativity involves the generation of useful novelty. Two modes of creating novelty are proposed: via new combinations of pre-existing primitives combinatoric emergence and via creation of fundamentally new primitives creative emergence.