Hybrid Elevations Using GAN Networks

منو

" Hybrid Elevations Using GAN Networks "
Mohammad, Ali S. A. Q. Beorkrem, Chris

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	1104532
Doc. No	:	TLpq2236474878
Main Entry	:	Beorkrem, Chris
	:	Mohammad, Ali S. A. Q.
Title & Author	:	Hybrid Elevations Using GAN Networks\ Mohammad, Ali S. A. Q.Beorkrem, Chris
College	:	The University of North Carolina at Charlotte
Date	:	2019
student score	:	2019
Degree	:	M.Arch.
Page No	:	58
Abstract	:	This project attempts to develop and test a method for generating one-sided hybrid exterior building elevations using two designer’s base criteria and design ruleset as an input. Architects are using computational design to expedite the iteration process in an efficient manner. Optimization techniques utilizing genetic solvers within the architectural 3D model space have been around for the past decade. However, with the introduction of artificial intelligence the computational design niche within the architectural field can be expanded on. Generative Adversarial Networks (GAN) are used in this research to demonstrate artificial intelligence capabilities in the computational design realm. Can GAN networks dream of hybrid architectural elevations?
Subject	:	Architecture
	:	Artificial intelligence
	:	Design