The Meat of AI: Architecture & Dataset Creation

Workshop at DigitalFUTURES 2021

We are happy to announce that the AR2IL (Architecture and Artificial Intelligence Laboratory) at Taubman College of Architecture and Urban Planning, University of Michigan, will be hosting a workshop at DigitalFUTURES this year. Have a look under the hood of the ongoing research at the AR2IL. (https://ar2il.com/) We are focussing on one of the underappreciated, but fundamentally crucial parts of working on AI applications: the creation of datasets. Join us and get credited as contributors to our research!

Apply here: https://www.digitalfutures.world/workshops/94.html

Deep Neural Networks are incredibly data-hungry; the high performance of these algorithms is heavily dependent upon the availability of giant training datasets. In the growing field of Deep Design and Architecture, there is a huge need for the collection/creation of comprehensive labeled datasets (in both the 2D image/plan realm as well as for 3D models).While this workshop will be a crash course instruction in Dataset Generation, including data creation and labeling methodology and tools, we will instruct students on how to create end-to-end machine learning pipelines. Specifically, how to formulate the desired task into a problem that is solvable with machine vision tools, how to design and generate a dataset that defines the world space for this task/problem space, and finally how one can train and evaluate an algorithm on their dataset.

With these tools, the students of this workshop will be able to participate in a very unique opportunity: they will be able to contribute as both annotators and creators to AR2IL’s effort to generate a novel Floor plan dataset, called Common House. The students will be credited as contributors to the dataset, and have opportunities to continue as annotators on the dataset in the months after the workshop.The AR2IL is an interdisciplinary laboratory between Taubman College (Matias del Campo, Michigan Robotics (Alexandra Carlson) and Computer Science (Danish Syed, Janpreet Singh).