Category: ARTIFICIAL DESIGN

Design Brain

ARTIFICIAL DESIGN, EXPERIENCE

Imagined as an ever-shifting spatial interface revealing the innermost dreams of an artificial machine pre-occupied by possible resilient futures of the Swiss refuge, “Design Brain” is a showcase of the outcome in the design research studio conducted at EPFL with master students in Spring 2020 called Refuge 2.0 – Artificial Swissness. In the studio, machine (…)

Zürich Prints

ARTIFICIAL DESIGN, URBAN

Models digitally printed by students as one of the final steps in the artificial design research process with GAN in Zürich. https://deepcityzurich.wordpress.com/ Keywords: GAN, Artificial Design, Zürichness, Housing, 3D Print Students: Bryan Parvex, Maylis Pillet, Ebrahim Rahmani, Marilyn Brühlmann, Andrea Calzoralo, Lara Giorla, Beatriz Menéndez Ontañón, Antoine Prat, Ricky Lee, Valérie Ovadia, Basile Sordet, Yonah (…)

Artificial Zürichness – Final Review

ARTIFICIAL DESIGN, CODING

Throughout the semester we reflected on what characterizes Zürich, what is Zürichness and if arriving at this solution through machine learning (and Generative Adversarial Networks – GANs) makes the result artificial. Does artificial intelligence create artificial architecture? In the final review, the individual projects resulting from the study were reviewed by a jury composed of (…)

Giro – Deep Façade

ARTIFICIAL DESIGN, CODING

This project was developed in the context of the “Artificial Zurichness” research. Deep Learning and Generative Adversarial Networks (GAN) were deployed as a project tool to capture and maintain the essence (genius loci) of a specific site – Zürich – while modifying the type of architecture through additions or variants. From here, a GAN image (…)

To Meditate – Virtual Zen Garden

ARTIFICIAL DESIGN, EXPERIENCE

Meditation is a practice where an individual uses a technique – such as mindfulness or focusing the mind on a particular object, thought, or activity – to train attention and awareness, and achieve a mentally clear and emotionally calm and stable state. In a global pandemic, various things can cause mental stress, anxiety and the (…)

Sampling Zürich

ARTIFICIAL DESIGN, CODING, URBAN

In this research experiment, the GAN algorithm serves as a new mode of vision, bypassing the preconceptions of the human designer in order to reveal an unbiased pool of ideas. The algorithm zeroes in on details otherwise unnoticed to generate new interpretations. The curation of the input data set and the critical analysis of the (…)

The fortress

ARTIFICIAL DESIGN

Can the essence of the computer generated image of a Swiss cabin be translated on site? How do colors and textures materialize in a realistic building proposal? Big data is a field that offers ways to analyse, systematically extract information from, or otherwise deal with data sets that are too large or complex to be (…)

Refuge Prints

ARTIFICIAL DESIGN

Models digitally printed by students as one of the final steps in the artificial design research process with GAN in Switzerland with a focus on the refuge. refugetwopointoh.wordpress.com Keywords: GAN, Artificial Design, Swissness, Housing, 3D Print Students: Eric Nardini, Romain Claus, Aina Rodriguez, Clara de Lapuerta, Christophe Gautier, Simone Izzo, Samuel Aeschimann, Núria Fàbrega, Mathieu (…)

3D GAN: Anamorphic Inverse Projections

ARTIFICIAL DESIGN

The exploration of the potential uses in architectural design shows that GANs are more suitable for learning and generating 2D images such as building facade and floor plans due to the exponential increase of computational cost in 3D model applications. GANs work natively with data that can be represented in numerical values. 2D image data (…)

Data Moiré

ARTIFICIAL DESIGN

The larger the dataset, the better the generated images in terms of photographic quality. The diversity of content within the dataset also was found to impact the generative capacity of GANs directly. The smaller variation in the dataset produced a more focused and better image, while the more variation in the dataset created more diverse (…)

Refuge Sampling

ARTIFICIAL DESIGN, CODING, EXPERIENCE

Data curation and GAN manipulation (or equivalent deep learning network) is used to create variations of artificially generated alpine refuges with the quality of “Swissness”, where the collection of facades of Swiss alpine architecture will serve as samples for the algorithms to explore how architects can use and interact with machine learning algorithms as a creative (…)

Refuge 2.0 – Artificial Swissness

ARTIFICIAL DESIGN, CODING, URBAN

In Refuge 2.0 – Artificial Swissness we examine the notion of “cultural resilience” in Alpine cities, and question the role of creative artificial intelligence and deep learning in architecture. Confronting the machine as an active design agent, we ask the following questions: Can machines automatically learn and generate meaningful architecture? Can they go beyond quantifiable data and optimization (…)