Portugal

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.

ICCC&#39;20

Deep Learning as Heuristic Approach for Architectural Concept Generation

architectural concepts

augmenting creativity

computational creativity

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.



technical paper

"

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."

Creativity Theatre for Demonstrable Computational Creativity

Co-Creativity and Support 1

Language and Narrative 1

Visual Creativity 1

Human and Machine Intelligence: a Music Information Retrieval Perspective

Performance

Music and Poetry 1

Philosophy and Evaluation 1

Visual Creativity 2

keynote

https://d3smihljt9218e.cloudfront.net/transcript/1799/subtitle/3c676ff33585cc017a6d0209235d8191.vtt

English (automatic)

Downloads

Next from ICCC'20

Under One Sky

Similar lecture

Post-creativity and AI: Reverse-engineering our Conceptual Landscapes of 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

Under One Sky

Similar lecture

Post-creativity and AI: Reverse-engineering our Conceptual Landscapes of Creativity

Downloads