AI in Architecture: How do machines create based on their memories?

About

Organised for London Festival of Architecture, this event is part of the Creative AI meetup series designed to promote artificial intelligence in the creative industries to an audience of technologists, artists and industry professionals.

There will be the following talks:

Ali Eslami, Research Scientist

"Artificial Intelligence and Computer Aided Design"

This talk will examine the possibilities of using data and machine learning techniques to create architectural designs, drawing on the recent developments in generative models and examples from product design.

S. M. Ali Eslami is a Research Scientist working on problems related to artificial intelligence. Previously he was a post-doctoral researcher at Microsoft Research in Cambridge. He did his PhD in the School of Informatics at the University of Edinburgh, during which he was also a visiting researcher in the Visual Geometry Group at the University of Oxford. His research is focused on getting computers to learn generative models of images that not only produce good samples but also good explanations for their observations.

Daghan Cam, CEO and co-founder of Ai Build

"Adaptive Autonomous Manufacturing with AI"

This talk will focus on practical applications of AI for manufacturing complex architectural forms with examples of built work from Ai Build. Industrial robots have been widely used in the manufacturing industry in the last few decades, most commonly to automate repetitive tasks by following instructions from a computer generated file with very little or no sensing and adaptation capability. We call this “blind automation”. At Ai Build, we give robots the ability to see and sense the environment for them to be able to make decisions on the fly by processing this data in real time. This is a paradigm shift from blind automation to autonomous manufacturing which makes the system resistant to unpredictable conditions in a construction site or on a factory floor. For example in large scale 3D printing, material behaviour is very important and very difficult to simulate precisely which leads to unpredictable structural failures if not taken into consideration. We are using a combination of simulation and real-time decision making algorithms to compensate for minor mistakes which might have accumulated into more severe structural failures if they were not taken into account.

Daghan Cam is the CEO and co-founder of Ai Build, a London based company developing Artificial Intelligence and Robotics technologies for large scale additive manufacturing. He is also a visiting lecturer at University College London doing research on robotic fabrication, 3d printing and parallel algorithms with GPU computing. His work focuses on developing intelligence for automating complex tasks in design and manufacturing by using computer vision and machine learning techniques. Before starting Ai Build, he worked at Zaha Hadid Architects and ran his own architectural design practice. He holds a masters degree with distinction from the Architectural Association.