Computational Design X Circular Economy
Machine Learning
for Adaptive Temporary Architecture
00
Brief
Tutored by Mateusz Zwierzycki
Online workshop
Machine learning can be a powerful tool to aid in the creation of adaptive architecture models and developing interesting possibilities in design that consider principles of a circular economy.
Switching architecture to become a circular economy poses new challenges in how we organize construction, utilization and recycling of our living spaces. Architects will not only design the building as an end product but also its entire timeline – how it’s conceived, how it’s used and what will happen with the materials after disassembly. In this context, machine learning can aid the architects in a range of ways among others:
- Predicting the usage patterns (wear and tear, maximizing use phase)
- Responding to the occupant’s needs (efficiency improvements)
- Intelligent scrap material evaluation (addressing recycling)
During this workshop, the participants will get a chance to learn about machine learning in the design context, with the applications ranging from the clustering of elements to space planning applications for generating interior architecture responsive to user needs. For that purpose a parametric model will be developed, which will serve as a data source. Using unsupervised and supervised learning techniques, the participants will then perform a range of tasks addressing the model solution space.
The first task will be to use clustering methods to discover families of possible designs. Dimensionality reduction using autoencoders will be used to select a subset of preferred solutions. Supervised learning will predict the indirect properties of the design based on user input. A survey will be designed to gather information about the user preferences regarding the design solution space, in an effort to prolong the usage phase and serve the users better (usage intensification).
No prior knowledge of AI or machine learning is required. A basic understanding of Grasshopper is required.
01
Topics
Topics and Contents covered during the workshop
- Supervised learning with neural networks
- Unsupervised learning with k-means clustering
- Data pre- and post-processing
- Data collection
02
Requirements
Required Software & Hardware and Skills
- Rhinoceros 6 (free versions available)
- Grasshopper Plugins installed: Owl + Lunchbox + Shortest walk
- A second monitor is highly recommended
Basic understanding of Grasshopper is recommended (you can register to our Computational Design for Beginners workshop).
Each participant needs to work from their personal computer.
The principal software is Rhinoceros 6.0. The 90-day trial version can be downloaded from the website www.rhino3d.com/eval.html . Grasshopper 3D will be the main computational tool.
Windows operating system is highly recommended since many of the Grasshopper plugins still do not run on Apple IOS operating systems.
03
Agenda
Calendar and Timetable
From March 11st to 17th, 2021.*
*excluding weekend.
Thursday to Wednesday from 4 pm to 8pm (Paris Time).
The workshop is an online learning experience including :
- 18 hours of live teaching
- 2 hours of Q&A
- chat support
Day 1
- Course overview
- Introduction to AI and machine learning
- Introduction to Owl
Day 2
- Preparing 3d model for analysis
- Extracting data from 3d models
- Unsupervised learning
Day 3
- Creating user survey
- Parsing data (CSV and Excel files) in Grasshopper
- Collecting data
Day 4
- Supervised learning introduction
- Training a simple XOR model
Day 5
- Supervised learning based on survey data
- Using user preferences in the design process
- Question & Answer
- Individual work
04
Other info
Other practical information
- Main Language: English
- Hosted on Zoom
- Chat support provided on Slack
- Minimum number of participants: the workshop will be activated with a minimum of 10 participants. Otherwise organizers can make the decision to cancel the event; in this case the tickets will be fully refunded.
05
Tutor
About the tutor
Mateusz Zwierzycki
Mateusz is a developer, an architect, and a researcher. He is an author of the Owl, Starling, Squid, Anemone, Mesh Tools plugins and many other Grasshopper-based plugins.
He is also the founder of the Object consultancy, the Milkbox group, long-time workshop tutor, teacher, and parametric design populariser. Currently a Research Assistant at Digital Design Methods Chair BTU Cottbus, where he’s pursuing his PhD thesis on AI in Architectural Design.
419 €
- - Early Birds Price is only available until February 21st
- - Educational tickets are only for students
- teachers and
- researchers (proof of status required)
- - TVA may apply following your invoicing address : please contact us for further details
509 €
- - Early Birds Price is only available until February 21st
- - TVA may apply following your invoicing address : please contact us for further details
Special Offer
Two seats at 50% discount!
Two seats at 50% are offered for selected students.
In order to apply for the discounted seats, please send an email to driven@volumesparis.org specifying the subject “Driven x Reflow / Machine Learning workshop 50” and including the following material by March. 3rd:
- A short paragraph listing your motivation (body of the email)
- A portfolio of your works
- Your declaration of honor of being fully available during the week of the workshop at the specified times
- A valid certificate of registration as a student