Pre-Conference Workshop Monday, July 29

1:00 pm - 5:00 pm
Managing Data & Leveraging the Potential of AI & Machine Learning
Workshop Leader: John Morrison, Architectural Designer, Corgan Workshop Leader: Petr Mitev, Design Computation Team Leader, NBBJ

AI offers the opportunity to optimize solutions and revolutionize the way architects design, but before AI serves as an intelligent assistant to architects, data you already have has to be prepared through proper cleaning, storage and integration. This workshop will open up with learning how to get your data ready for more advanced machine learning – cleaning, storing and connecting data.
Following that, you will be submerged in a crash-course in accessible and practical machine learning for design and construction, with a focus in computer-vision models. We will use the time to learn about popular ML models by building our own small applications which will use the models to generate analysis on different types of data.
The workshop models will be centered around the growing field of computer-vision and we will also dive into making models to analyze our collected data. For this workshop, we’ll be using Javascript to leverage Google’s Tensorflow library for the creation of our models and for the serving of the models’ outputs. All skill levels are welcome, and those with experience with a dynamically interpreted language such as Javascript or Python are especially encouraged to attend.
Take Aways:
Real-time Spatial Analysis – Using Google’s coco-ssd and mobile-net v2 models, we’ll extract information from images/videos that come from a simple IOT sensor camera (or a webcam for the purpose of the workshop) which can be used to inform design and/or a post-occupancy evaluation of a space. Some of the types of information we’ll try to extract are:
  • How many people are in the space.
  • Whether the space is highly trafficked, or it is a sedentary meeting spot.
  • What other kinds of objects/entities are in the space.
  • Whether any custom objects are present (type of furniture, plant, light, etc.)
We can use the collected data to make predictions such as:
  • When the space will be most/less occupied (when lighting and HVAC systems should be turned down/up).
  • What kind of furniture distribution is optimal for the space (how much seating spaces, standing, meeting spots, informal gathering, etc.)?
 

John Morrison, Architectural Designer, Corgan

Petr Mitev, Design Computation Team Leader, NBBJ