Encoded Memory V1.0 workshop - April 4-8, Dubai (United Arab Emirates)

Encoded Memory V1.0 workshop
April 4-8, 2017
from 10:00 to 18:00
Dubai Knowledge Village
Dubai (United Arab Emirates)

Encoded Memory V1.0 is an advanced Grasshopper workshop which aims to explore the potential of machine learning neural networks in the development of an urban fabric of a particular sector in Dubai.

“(…) We will demonstrate how the parametric model is presented to the network and how it influences its effectiveness and decisions making process in directing the design workflow. We will be testing multiple data input and will explore the network response based on the self-learning generative nature of the network. Based on the network interpretation to the input data, participants will be able to visualize the network growth outcome, and understand its data interpretation and decision making process and be able to intervene to adjust these data, or the outcome, to influence the network future direction. Behavior of the system will therefore develop by assessing their propagation on a basic organization level, then developing it to work on a variety of urban levels”.


"During this workshop we will investigate the applications of neural networks in multiple roles - from the designer’s adviser to the self-learning, generative method. We will try to employ those methods in our decision-making process, learning how they can assist us in the exploration of the parametric space. In order to utilize the machine learning tools, we need to know exactly how they work. To do that, we will closely monitor the neural network training and decision making process, and learn how it responds to the data.

We will be using Rhino/Grasshopper with selected plug-ins such as Owl (yet to be released to public) for the generation of the neural network, based on the input data from each participant or a group. The selected data and their connections reflect the design intent as set by each group. The network will process these data and will propose different layouts as it propagates the field. Participants will be able to visualize the propagation, and to guide the outcome to reflect their design intent".


  • Machine learning concepts and notions (supervised vs unsupervised learning, neural networks, clustering etc.)
  • Application of machine learning in expanding the design space, and generating different possibilities based on the design intent.
  • Engaging with the machine learning process, and guiding the possible outcomes.
  • Data preparation for machine learning - ways of model parametrization
  • Scripting with Owl
  • Accord framework basics

Mateusz Zwierzycki / Poland
Member @ DesignMorphine
Research Assistant @ CITA
MArch ASP Poznan University of Arts, Poland

Zayad Motlib / United Arab Emirates
Founder @ D-Nat
Head of Design @ Al-Nhayan Design Office


To participate, you should provide your own computer with the following software installed:

Late registration until March 21, 2017.

More info…
Facebook event…

Posted Feb 16, 2017 by Elena Caneva on Rhino News, etc.