重编程
生成语法
创造力
计算机科学
人工神经网络
块(置换群论)
空格(标点符号)
发条
人工智能
人机交互
心理学
数学
地理
操作系统
遗传学
社会心理学
生物
考古
细胞
几何学
标识
DOI:10.52842/conf.ecaade.2020.1.249
摘要
The democratization of design requires balancing all sorts of factors in space design.However, the traditional way to organize spatial relationships cannot deal with such complex design objectives.Can one find another form of creativity rather the human brain to design space?As Margaret Boden mentioned, "computers and creativity make interesting partners with respect to two different projects."This paper addresses whether machine creativity in the form of neural networks could be considered as a powerful generative tool to reprogram urban block in order to meet multi-users' needs.It tested this theory in a specific block model called Agri-tecture, a new architectural form combing farming with the urban built environment.Specifically, the machine empowered by Generative Adversarial Network designed spatial layouts based on learning the existing cases.Nevertheless, since the machine can hardly avoid errors, architects need to intervene and verify the machine's work.Thus, a synergy between human creativity and machine creativity is called for.
科研通智能强力驱动
Strongly Powered by AbleSci AI