DANIEL BOLOJAN NONSTANDARDSTUDIO

Daniel is the founder of Nonstandardstudio, Ph.D. candidate at Die Angewandte (Vienna, Austria) and an Assistant Professor at School of Architecture, Florida Atlantic University. His current research focuses on the development and the application of deep learning strategies in architectural design, addressing topics of shared-agency, augmentation of designer’s creativity and perception. After graduating from Studio Zaha Hadid (Vienna, Austria) he joined the internationally renowned architecture office CoopHimmelblau as a Computational Design Specialist, Founder and Head of Chbl|Code. As Head of Chbl|Code, he held the role of developing custom computational design tools, computational design strategies, machine learning and deep learning applications. He is responsible for the office’s current drive to develop deep learning strategies aimed at the augmentation of the designer’s native abilities through the development of the DeepHimmelblau Neural Network. Over the years, he has taught several design studios and seminars at the Institute of Structure and Design – University of Innsbruck, Florida International University (Miami), and held numerous international workshops (Harvard GSD, Die Angewandte, I.sd (Innsbruck), FIU (Miami) etc.) on the application of complex systems and neural networks to architectural design.

.


Gaudi + Neural Networks

This ongoing research looks at the development of a neural network capable of identifying relevant compositional features in a collection of Antoni Gaudi – Sagrada Familia samples and samples from nature. The goal here is not to transfer one domain’s style to another, but rather to transfer one domain’s underlying compositional characteristics to another domain. Similar to the way humans learn, by sorting and filtering irrelevant information, the neural network learns to discriminate towards less relevant compositional features while enhancing the relevant ones. A very common design practice is that a designer will learn, consciously or unconsciously semantic representation of one domain (nature, sails etc.). The learned representation is than later reinterpreted through a particular filter e.g. architectural style, architectural culture etc., and translated into a different domain (design, architecture etc.).

© nonstandardstudio
© 2020 nonstandardstudio


Agent based creative ai

The project explores the use of 3D Deep Neural Networks to learn design intents and generate design spaces. Design intent is used here to describe architects/designer desire, sensibilities, or design criteria. It may refer to aesthetics, form, structure, affects or any other aspects of architecture. Design space is defined here as the multidimensional combination and interaction of design input variables and design process parameters that represent the design intent.

© 2018 nonstandardstudio
© 2018 nonstandardstudio
© 2018 nonstandardstudio

.

Deep himmelblau

DeepHimmelb(l)au is the result of the cumulative research effort undertaken by Coop Himmelb(l)au which operates at the intersection between architecture, practice and AI/Deep Learning.

DeepHimmeb(l)au is an experimental research project led by Design Principal Wolf D. Prix, Design Partner Karolin Schmidbaur and Chbl’s Computational Design Specialist Daniel Bolojan, which explores the potential of teaching machines to interpret, perceive, to be creative, propose new designs of buildings, augment design workflows and augment architect’s / designer’s creativity. DeepHimmelb(l)au is currently the most advanced research dealing with the design potential of AI/deep learning undertaken by any architectural office.

© 2019 coop himmelb(l)au © nonstandardstudio

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s