Evolutionary trends in the use of artificial intelligence in support of architectural design

IF 0.4 0 ARCHITECTURE

Techne-Journal of Technology for Architecture and Environment Pub Date : 2023-05-30 DOI:10.36253/techne-13739

G. Brunetti

引用次数: 0

Abstract

The paper analyses the evolutionary tendencies in the use of artificial intelligence in building design, highlighting: a) the ground lost by knowledge-based expert systems and the diffusion of systems combined with heuristic and stochastic approaches; b) the spread of evolutionary algorithms in the field of optimisation; c) a climax of the influence of probabilistic approaches around 2010; d) the progressive dominance of deep learning since 2012. It is likely that the next step requires hybridisation of deep learning and symbolic artificial intelligence, and it is expected that the contribution of design domain experts in terms of knowledge formalisation will be a fundamental driver of it.

查看原文本刊更多论文

人工智能在建筑设计中应用的发展趋势

本文分析了人工智能在建筑设计中应用的演变趋势，强调了:a)基于知识的专家系统和启发式和随机方法相结合的系统的扩散所失去的基础;B)进化算法在优化领域的传播;C)概率方法的影响在2010年前后达到高潮;D)自2012年以来深度学习逐渐占据主导地位。下一步很可能需要深度学习和符号人工智能的混合，预计设计领域专家在知识形式化方面的贡献将是它的基本驱动力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Techne-Journal of Technology for Architecture and Environment ARCHITECTURE-

CiteScore

0.60

自引率

33.30%

发文量

审稿时长

8 weeks

期刊介绍： TECHNE, Journal of Technology for Architecture and Environment is the scientific magazine of SITdA, the Italian Society of Architectural Technology. Techne aims: to publicize significant contributions in the technological and environmental planning action area, to provide a tool for international comparison on research themes in that area, to promote the recognition of scientific contributions in accordance with its criteria on the evaluation of research in an academic context and to promote the circulation of contributions concerning research and experimentation, the results and effects of which are interesting in terms of social, economic, environmental and cultural impact. The magazine endorses an editorial policy primarily geared towards the diffusion of knowledge, favouring access to it and ensuring reliable and original contributions as well as recognition to the authors, whose protection is a top priority but not limiting. Techne publishes two issues a year; it includes articles, essays, columns, interviews and reviews by authors who work in the academic world, in research, design, industry, and entrepreneurial and client organizations.