Artificial Intelligence | Online Workshop | English | North-South Americas
Description:
This incremental 5-day workshop will cover a series of hands-on machine learning techniques, including but not limited to 2D Style Transfer, 2.5D Generative Models and 3D Generative Models with 3D-VAE-GAN. The workshop will be project based, where participants will be asked to develop or customize generative architectural designs based on provided sample workflows.
This workshop will provide an introduction to Machine Intelligence(MI)—Artificial Intelligence and Machine Learning—in the field of Architecture, Design and Art. Through a series of lectures and hands-on workshops, participants will be given a historical introduction to MI-aided design, offered a view of the current state-of-the-art in terms of knowledge and tools, and a perspective on its future potential illustrated through real-world projects.
We will also examine the various types of machine intelligence that are applied as cutting-edge generative architectural design techniques since the invention of the concept “Computer-Aided Architectural Design” (Mitchell Williams 1975). By transplanting similar theoretical frameworks from computational cognitive neuroscience (David Marr 1982), we propose the universal computational model of generative architectural design as the approach towards creating architectural design machines that can possibly pass certain categories of Turing Tests (Alan Turing 1950). We will also invite guest lecturers from the Harvard Graduate School of Design to discuss both practical and theoretical applications of Machine Intelligence in Architectural Design.
More specifically, we will cover the following topics for architecture and Machine Intelligence:
1. How to use RunwayML for image generation, style transfer
2. How to connect RunwayML to Rhino-Grasshopper
3. How to generate 2.5D/3D shape using image processing and image lofting techniques
4. How to use prepare dataset, training with 3DGAN
5. How to deploy 3DGAN model with Flask and connect with Rhino-Grasshopper
6. How to use 3DGAN for shape synthesis in voxel format
7. How to use 3DGAN for real-time inference and visualization with Latent Walk
8. Gain basic understanding of reinforcement learning and computational congnitive science
9. Learn how machine intelligence is used in the AEC industry
Key Words:
Artificial Intelligence,Generative Adversarial Networks,Architectural Design,
Required Skills:
Experience with 3D Modeling Software such as Rhino is a Plus, but not necessary
Required Software:
Rhinoceros 7
Required Hardware:
Windows PC Required
Maximum number of participating students:
20
This workshop will provide an introduction to Machine Intelligence(MI)—Artificial Intelligence and Machine Learning—in the field of Architecture, Design and Art. Through a series of lectures and hands-on workshops, participants will be given a historical introduction to MI-aided design, offered a view of the current state-of-the-art in terms of knowledge and tools, and a perspective on its future potential illustrated through real-world projects.
We will also examine the various types of machine intelligence that are applied as cutting-edge generative architectural design techniques since the invention of the concept “Computer-Aided Architectural Design” (Mitchell Williams 1975). By transplanting similar theoretical frameworks from computational cognitive neuroscience (David Marr 1982), we propose the universal computational model of generative architectural design as the approach towards creating architectural design machines that can possibly pass certain categories of Turing Tests (Alan Turing 1950). We will also invite guest lecturers from the Harvard Graduate School of Design to discuss both practical and theoretical applications of Machine Intelligence in Architectural Design.
More specifically, we will cover the following topics for architecture and Machine Intelligence:
1. How to use RunwayML for image generation, style transfer
2. How to connect RunwayML to Rhino-Grasshopper
3. How to generate 2.5D/3D shape using image processing and image lofting techniques
4. How to use prepare dataset, training with 3DGAN
5. How to deploy 3DGAN model with Flask and connect with Rhino-Grasshopper
6. How to use 3DGAN for shape synthesis in voxel format
7. How to use 3DGAN for real-time inference and visualization with Latent Walk
8. Gain basic understanding of reinforcement learning and computational congnitive science
9. Learn how machine intelligence is used in the AEC industry
Schedule:
Jun 28 - Jul 2
-
Day 1 / Jun 28
-
Day 2 / Jun 29
-
Day 3 / Jun 30
-
Day 4 / Jul 1
-
Day 5 / Jul 2
Instructors:
-
Runjia Tian Harvard Graduate School of Design,ResearcherRunjia Tian is a Master in Design Studies, Technology Concentration student at Harvard Graduate School of Design. Trained as an architect, Runjia is a multidisciplinary advocate of architecture, computation, and engineering. He investigates the future of design through the synergetic engagement of creative computation, extended reality, multimodal media, machine perceptions and deep learning. His more recent research focuses on the enactive co-creation between human designers and artificial intelligence. Runjia's research has been supported by Harvard Joint Center for Housing studies student research support grant, MDes Research and Development Award, Harvard Graduate School of Design Summer Research Grant and MIT designX. Advised by Dr. Garcia del Castillo Lopez, Jose Luis, Runjia's resent thesis research at the GSD involves the use of deep reinforcement learning and human-centric artificial intelligence in the generative architecture design process. Runjia has authored/co-authored several peer-reviewed publications on architecture, urban design, and technology in international conferences such as CDRF, ACADIA, eCAADe and CAADRIA. He is the Co-founder of AiRCAD, with research and working experience at Harvard Graduate School of Design, Harvard Map of Inclusive Place and SymbolsMIT CSAIL, MIT Department of Architecture Design Computation Group and Autodesk Boston. He has also served in the teaching team for the GSD SCI 6338 Introduction to Computational Design and GSD SCI 6365 Enactive Design course, and have taught the Game Jam Interactive Geometry during JTerm at the GSD. For more details on Runjia's work, please kindly visit https://runjiatian.work/. -
George Guida Harvard Graduate School of Design,Student + ResearcherGeorge Guida is an ARB RIBA architect and creative technologist currently pursuing a Masters at Harvard GSD. His main interests lie at the intersection between equity, design, and technology through the lens of computation, machine intelligence, and mixed realities. His latest research focuses on creative applications of 2D and 3D machine learning in the context of generative architecture design and urban city planning. Originally from Rome, George holds a diploma from the Architectural Association. He is currently a research assistant at the Laboratory for Design Technologies, and has previously worked in leading firms in Italy, Kuwait, and most recently at Foster + Partners in London as an architect and LEED AP. -
Dongyun Kim Harvard Graduate School of Design,Student + ResearcherDongyun Kim is an architecture and computational designer. He explores the connection between technological advancement and architectural design because he believes that architectural innovation has been powered by technological advancements. His current interests are focused on the application of Artificial Intelligence into the architecture discipline, generative design methodologies, and robotics. Dongyun is currently a graduate student in Master in Design Studies with a concentration on Technology at Harvard University Graduate School of Design, working as Research Assistant at Laboratory for Design Technologies. He received a Master of Science in Design (Advanced Architectural Design) from the University of Pennsylvania Weitzman School of Design where he was awarded the Korean Government Scholarship Program for Study Overseas. He also holds a Bachelor of Architecture from Hongik University in Seoul.