Portugal

&quot;In this paper we consider the notion of dialogic creative ar- tificial intelligence (DCAI) systems, where co-creativity be- tween a human user and a computational system is supported through dialogic interaction. By dialogue we mean both tra- ditional language-based communication for explicit critique and persuasion (dialogue about creative artefacts) as well as a broader potentially non-linguistic notion of dialogue that emerges through the exchange of suggestions and changes (dialogue through creative artefacts). To capture this, we de- fine DCAI as occurring when both system and user are able to influence each others’ creative objectives. The paper mo- tivates our pursuit of dialogic interaction and provides some explanation of why we have defined it through its impacts rather than its mechanism of action. We provide two anal- yses to support our argument: an exploration of a commer- cial creativity support tool that has an extensive vocabulary for describing artefacts abstractly but does not meet our def- inition of dialogic interaction, and a case study of a creative interaction between two human professionals that exhibits di- alogic interaction throughout. For the latter we consider how studies of human-human co-creation can offer non-obvious design concepts that might be applied to co-creative DCAI systems.
&quot;

ICCC&#39;20

A Speculative Exploration of the Role of Dialogue in Human-Computer Co-creation

dialogic creative ai

co-creativity

"In this paper we consider the notion of dialogic creative ar- tificial intelligence (DCAI) systems, where co-creativity be- tween a human user and a computational system is supported through dialogic interaction. By dialogue we mean both tra- ditional language-based communication for explicit critique and persuasion (dialogue about creative artefacts) as well as a broader potentially non-linguistic notion of dialogue that emerges through the exchange of suggestions and changes (dialogue through creative artefacts). To capture this, we de- fine DCAI as occurring when both system and user are able to influence each others’ creative objectives. The paper mo- tivates our pursuit of dialogic interaction and provides some explanation of why we have defined it through its impacts rather than its mechanism of action. We provide two anal- yses to support our argument: an exploration of a commer- cial creativity support tool that has an extensive vocabulary for describing artefacts abstractly but does not meet our def- inition of dialogic interaction, and a case study of a creative interaction between two human professionals that exhibits di- alogic interaction throughout. For the latter we consider how studies of human-human co-creation can offer non-obvious design concepts that might be applied to co-creative DCAI systems.
"

technical paper

Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviours that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalising what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.


ICCC'20

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.
Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviors that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalizing what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.



We aim to help bridge the research fields of generative deep learning and computational creativity by way of the creative AI community, and to advocate the common objective of more creatively autonomous generative learning systems. We argue here that generative deep learning models are inherently limited in their creative abilities because of a focus on learning for perfection. To highlight this, we present a series of techniques which actively diverge from standard usage of deep learning, with the specific intention of producing novel and interesting artefacts. We end by describing how a two-way bridge between the research fields could be built.

Bridging Generative Deep Learning and Computational Creativity

Co-creativity research is thriving in a wide variety of domains, but we lack the vocabulary to talk about capabilities and progress across all those domains. We propose a framework to facilitate comparing how co-creative systems augment creativity. We draw on domain-agnostic concepts in interaction design research. Our framework describes the different aspects of interactions between one or more humans and their computationally creative collaborators at three levels: interaction modalities, interaction styles and interaction strategies.

Modalities, Styles and Strategies: An Interaction Framework for Human–computer Co-Creativity

This paper introduces EMILY, a machine that aims to createoriginal poems in the style of renowned poet Emily Dickin-son. Dickinson’s succinct and syntactically distinct style withunconventional  punctuation  makes  for  an  interesting  chal-lenge for automated poetry creation.  A user study comparesEMILY’s poems to Emily Dickinson originals, demonstratingthe machine’s ability to evoke mental images and highlight-ing challenges for future work.

EMILY: An Emily Dickinson Machine

Human collaboration with systems within the Computational Creativity (CC) field is often restricted to shallow interactions, where the creative processes, of systems and humans alike, are carried out in isolation, without any (or little) intervention from the user, and without any discussion about how the unfolding decisions are taking place. Fruitful co-creation requires a sustained ongoing interaction that can include discussions of ideas, comparisons to previous/other works, incremental improvements and revisions, etc. For these interactions, communication is an intrinsic factor. This means giving a voice to CC systems and enabling bi-directional communication channels between them and their users so that they can: explain their processes and decisions, support their ideas so that these are given serious consideration by their creative collaborators, and learn from these discussions to further improve their creative processes. For this, we propose a set of design principles for CC systems that aim at supporting greater co-creation and collaboration with their human collaborators.

Explainable Computational Creativity

Machines are used to be well-known for doing repetitive jobs, following code produced by humans, so not often imagined as capable of producing unexpected results without direct human intervention in each unique case. The generative art broke this boundary by incorporating random variables extracted from a natural phenomenon into the coded environment. Using this method, our project introduces physical laws into 3D printing instructions; a custom slicer and G-Code compiler were developed, allowing manipulation of Z-heights of extrusions from the 3D printer so gravity can be used to generate randomness in 3D outputs. As a result, unique organic and porous forms could be created from the 3D printing process, differing from traditional, watertight solid prints.

Printing Error: Creating Uniqueness

The human condition can be characterised as the most essential characteristics, events and situations which describe human existence. We propose that a parallel discussion of the machine condition could improve public understanding of computational systems in general, and advance perception of creativity in computational creativity systems in particular. We present a framework for machines to creatively express their existence, sketch some aspects of the machine condition, and describe potential benefits of this approach.

On The Machine Condition and its Creative Expression

Do digital agents do Dadaism? To answer this question, we review a series of theatrical experiments involving human improvisers and AI-controlled Cyborgs in front of audiences. We describe these experiments and discuss the use of conversational digital agents (DA) on the stage. We identify two basic strategies of staging machines: the “immersive approach”, and the “Dadaistic approach”. We draw on Dadaistic conceptions of embracing modernity specifically in the Dadaists’ obsession with androids and cyborgs. Through analysis of several stage experiments we contend that digital agents, while attempting to build believable characters, do Dada, only if we do Dada too.

Do Digital Agents do Dada?

This work discusses the use of machine learning for extending the boundaries of architectural concepts. The use of deep learning algorithms is exploited for transferring stylistic attributes from one visual (archi-tectural) domain to another (architectural or other-wise). The combination of various semantic features into hybrid results helps locate possibilities for further exploration of one domain. The process is regarded as open-ended, taking advantage of a generative ad-versarial network’s (cycleGAN) capacity to “imagine” new results which may set the base for new morpho-logical or structural architectural paradigms. We are interested to situate the training results within the con-text of human and computational creativity, embrac-ing the capacity of automated heuristic methods to produce novel outcomes which can augment human decision making in design and architecture.

Deep Learning as Heuristic Approach for Architectural Concept Generation

"

For nearly 10 years, I have been downloading all the YouTube videos of the sky I could find using the words “sky” and “clouds” translated into many languages. To date, I have collected hundreds of these videos.

All over the world, people are captivated by the sky. They record it using their smartphones or with DSLR cameras to create time-lapse sequences. Sometimes these videos are created to be used for meditation or during prayer at church. Sometimes people simply want to share the beauty that they see in the world with others. They add music earnestly attempting to express how they feel looking up at the sky. They upload these videos in a generous, asynchronous act of sharing. YouTube is notorious for its toxicity, but there are no cruel comments on YouTube sky videos. Commenters give compliments and say thank you for sharing as well as make polite requests to use the clouds themselves. The original poster says thank you for the compliments and thanks people for reaching out for permission to use the video. Often the original poster also expresses interest to see people’s projects and how they used the skies. There’s only kindness and generosity.

I wrote a C++ program and OpenGl shader to combine these sky videos. When this program runs, it generates a collective sky synthesized from the skies captured by real people all over the world. The accompanying generative sound track is made from the original soundtracks of the sky videos that you are seeing blended on the screen. This work can run forever never producing exactly the same visuals or sound. The structure of the algorithmically generated visualization and soundtrack reflects the structure of the asynchronous online interaction between strangers engaged in this generous act of sky sharing. This is an example of a simple but beautiful, unintentional social network created through sharing videos of the sky.

During this unprecedented time of social distancing, we live under one sky, both together and apart."

Under One Sky

"
While the quality of computationally generated artefacts continues to improve, some people still find it difficult to accept software as being creative. To help address this issue, we introduce the notion of creativity theatre, whereby computational creativity systems demonstrate their creative behaviours, not only for the purpose of producing valuable artefacts, but also to heighten the sense that observers have of it being creative. We present an approach to this whereby an entirely separate AI system controls a casual creator app, which is normally used as a creativity support tool by people. We describe the ‘Can You See What I Can See?’ installation which performs such creativity theatre, and describe its operation in a recent open house event."

Downloads

Next from ICCC'20

Bridging Generative Deep Learning and Computational Creativity

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ICCC'20

Bridging Generative Deep Learning and Computational Creativity

Downloads