CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References
id ecaade2021_158
authors Joyce, Sam Conrad and Nazim, Ibrahim
year 2021
title Limits to Applied ML in Planning and Architecture - Understanding and defining extents and capabilities
source Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 243-252
doi https://doi.org/10.52842/conf.ecaade.2021.1.243
summary There has been an exponential increase in Machine Learning (ML) research in design. Specifically, with Deep Learning becoming more accessible, frameworks like Generative Adversarial Networks (GANs), which are able to synthesise novel images are being used in the classification and generation of designs in architecture. While much of these explorations successfully demonstrate the 'magic' and potential of these techniques, their limits remain unclear, with only a few, but crucial, discussions on underlying fundamental limits and sensitivities of ML. This is a gap in our understanding of these tools especially within the complex context of planning and architecture. This paper seeks to discuss what limits ML in design as it exists today, by examining the state-of-the-art and mechanics of ML models relevant to design tasks. Aiming to help researchers to focus on productive uses of ML and avoid areas of over-promise.
keywords Machine Learning; Artificial Intelligence; Creativity
series eCAADe
email
full text file.pdf (8,635,420 bytes)
references Content-type: text/plain
Details Citation Select
100%; open Ahmed, E, Saint, A, Shabayek, AER, Cherenkova, K, Das, R, Gusev, G, Aouada, D and Ottersten, B (2019) Find in CUMINCAD A Survey on Deep Learning Advances on Different 3D Data Representations , arXiv:1808.01462 [cs]

100%; open Brown, NC and Mueller, CT (2019) Find in CUMINCAD Quantifying Diversity in Parametric Design: A Comparison of Possible Metrics , AI EDAM, 33, pp. 40-53

100%; open Brown, TB, Mann, B, Ryder, N, Subbiah, M, Kaplan, J, Dhariwal, P, Neelakantan, A and ., et al (2020) Find in CUMINCAD Language Models Are Few-Shot Learners , arXiv:2005.14165 [cs]

100%; open Chaillou, S (2020) Find in CUMINCAD ArchiGAN: Artificial Intelligence x Architecture , Yuan, PF, Xie, M, Leach, N, Yao, J and Wang, X (eds), Architectural Intelligence: Selected Papers from CDRF 2019, Springer, Singapore

100%; open Cristie, V and Joyce, SC (2019) Find in CUMINCAD GHShot , Proc. eCAADe/SIGraDi 2019

100%; open Daniel, D (2013) Find in CUMINCAD Modelled on Software Engineering: Flexible Parametric Models in the Practice of Architecture , Ph.D. Thesis, RMIT

100%; open Del Campo, M (2021) Find in CUMINCAD ARCHITECTURE, LANGUAGE AND AI:Language, Attentional Generative Adversarial Networks (AttnGAN) and Architecture Design , Proc. CAADRIA 2021

100%; open Frey, CB and Osborne, MA (2017) Find in CUMINCAD The Future of Employment: How Susceptible Are Jobs to Computerisation? , Technological Forecasting and Social Change, 114, pp. 254-280

100%; open Fujimura, R (2018) Find in CUMINCAD The Form Of Knowledge, The Prototype Of Architectural Thinking And Its Application , Toto

100%; open Gero, JS (2002) Find in CUMINCAD Computational Models of Creative Designing Based on Situated Cognition , Proc. 4th Conf. on Creativity & Cognition

100%; open Harding, J, Joyce, S, Shepherd, P and Williams, C (2013) Find in CUMINCAD Thinking Topologically at Early Stage Parametric Design , Advances in Architectural Geometry 2012, 2012, pp. 67-76

100%; open Heaven, D (2019) Find in CUMINCAD Why Deep-Learning AIs Are so Easy to Fool , Nature, 574, pp. 163-166

100%; open Ibrahim, N and Joyce, S.C (2019) Find in CUMINCAD User Directed Meta Parametric Design for Option Exploration , Proc. ACADIA 2019.

100%; open Joyce, S.C and Ibrahim, N (2017) Find in CUMINCAD Exploring the Evolution of Meta Parametric Models , Proceedings of ACADIA 2017

100%; open Karras, T, Laine, S and Aila, T (2019) Find in CUMINCAD A Style-Based Generator Architecture for Generative Adversarial Networks , Proc. IEEE/CVF Conf. Comp. Vision and Pattern Recogn.

100%; open Koch, G, Zemel, R and Salakhutdinov, R (2015) Find in CUMINCAD Siamese Neural Networks for One-shot Image Recognition , Proc. of 32nd Int. Conf. on Mach. Learning

100%; open Machairas, V, Tsangrassoulis, A and Axarli, K (2014) Find in CUMINCAD Algorithms for Optimization of Building Design: A Review , Renewable and Stust. Energy Rev., 31, pp. 101-112

100%; open Mohiuddin, A, Woodbury, R, Ashtari, N, Cichy, M and Mueller, V (2017) Find in CUMINCAD A Design Gallery System: Prototype and Evaluation , Proc. ACADIA 2017

100%; open Nauata, N, Chang, KH, Cheng, CY, Mori, G and Furukawa, Y (2020) Find in CUMINCAD House-GAN: Relational Generative Adversarial Networks for Graph-Constrained House Layout Generation , arXiv:2003.06988 [cs]

100%; open Newton, D (2019) Find in CUMINCAD Generative Deep Learning in Architectural Design , Technology|Architecture + Design, 3, pp. 177-189

last changed 2022/06/07 07:52
pick and add to favorite papersHOMELOGIN (you are user _anon_1161 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002