Encoded Memory: Artificial Intelligence and Deep Learning in Architecture

Encoded Memory: Artificial Intelligence and Deep Learning in Architecture

Alberto Tono (San Francisco Computational Design Institute, USA), Hannah Tono (Dreamship, USA) and Andrea Zani (Eckersley O'Callaghan, USA)
Copyright: © 2020 |Pages: 23
DOI: 10.4018/978-1-7998-1234-0.ch012

Abstract

This chapter provides an overview of some artificial intelligence applications in the architecture, engineering, and construction industry. Furthermore, the authors will define Creativity and its limits for the machine in the role of architecture. This chapter raises the importance of start developing framework for artificial intelligence applications and big data to create the fundamental to further developments. Moreover, the importance of sharing data and train models in an open-source community will become a great asset to the development of our industry. In the future, Industry 4.0 will see more entrepreneurs in the field of architecture, engineering, and construction.
Chapter Preview
Top

Introduction

The general perspective of this chapter is to show the importance of harvesting, analyzing and connecting data to provide meaningful insights to all architects and engineers involved in the process of designing buildings (Appendix 3).

The Big Data extrapolated from this process can frequently display hidden connections between humans and their design processes. The insights collected by this inner connection of apparently irrelevant data, that are provided by the human interaction with machines, can minimize the margin of human errors. Unlocking encrypted information, also seen as the architects and engineer’s hidden memory, will allow to hand down the knowledge between different professional generations. Thus, this will be shown as encoded memory. The chapter will stress on the importance of various artificial intelligence (AI) applications focusing on human-machine interaction and can be divided into different sections:

  • The first is about the state of the industry providing some historical background.

  • The second part will cover the main limitations for the uptake of these technologies: will AI replace human creativity, especially when it comes to design?

  • After this digression, many practical applications examples will be introduced such as generative design in AI, computer vision, 3D reconstruction of point cloud and many others related to Building Information Modeling (BIM) Model and how to approach to the Building Knowledge Modeling (BKM) systems.

This chapter is focusing on the software part of this industrial revolution 4.0 more specifically on AI. It will not explain all the hardware components related to Computer Process Unit (CPU) vs Graphic Process Unity (GPU) conversation nor the cloud computing power needed to run these algorithms successfully. However, it will be centered on the impact of the upcoming technologies enabled by AI in the architecture, engineering and construction (AEC) space. In order to provide a historical background of the AI’s history, it is important to take in consideration the three winters that AI has overpassed and approached the subject from a practical and scientific point of view.

Top

Encoded Memories

Software is eating the world, Marc Andreessen on the 20th of August 2011 published it in the Wall Street Journal (Andreessen, 2011). This powerful sentence embeds all the values that software companies were bringing to the world at that point in time. Is this sentence true in today’s architectural and construction industry?

Robert Otani is the Chief Technology Officer (CTO) at Thornton Tomasetti, a leading consulting firm in engineering with a team of 20 Researchers and developers, furthermore he is specialized in computational design and BIM workflows. His point was to prove how software and technologies helped the growth of all different industry verticals except for the construction industry, which seems to slumber for many different reasons: demand of drawing and production from the architects, field in which creativity is dominant, different business models, job related to the minimal offer and not focusing on better quality, legal liability, amongst others (Deutsch, 2013). Furthermore, this graph shows how important is to innovate and focus on new technological opportunities such as AI, machine learning and deep learning for the architecture industry. There are endless opportunities to grow and to be disruptive for a gleeful future. Nowadays the attention has shifted to how humans can collaborate with AI agents and how they communicate between each other’s The grand irony of our times is that the era of computers is over. The most promising technologies are focused on the communication between computers (Kelly, 1997) to improve society. In fact, it seems like the “Software” is in the main phase of the digestive system and at this moment it is up to the human beings to decide to see the end of the cycle or to be integrated in the main organism, constituted by the synergy between these two entities: human and machine.

Moreover, this implies a great and deeper conversation that unfortunately is not the focus of this chapter, but it is possible to find a plethora of details about it in Federico Faggin’s new book: Silicio (Faggin, 2019) that dig deeper into the consciousness (Hall, 2007).

Key Terms in this Chapter

Open-Source: Denoting software for which the original source code is made freely available and may be redistributed and modified.

Biases: Cause to feel or show inclination or prejudice for or against someone or something.

Points Cloud: It is a set of data points in space. Point clouds are generally produced by 3D scanners, which measure many points on the external surfaces of objects around them.

Computer Vision: Is an interdisciplinary scientific field that deals with how computers can be made to gain high-level understanding from digital images or videos. From the perspective of engineering, it seeks to automate tasks that the human visual system can do.

Big Data: Extremely large data sets that may be analyzed computationally to reveal patterns, trends, and associations, especially relating to human behavior and interactions.

Machine Learning: is The scientific study of algorithms and statistical models that computer systems use to effectively perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence.

Historical Building Information Modeling: Acronym for Historical Building Information Modelling, 3D modeling information system for cultural heritage and historical building. It uses the BIM (Building Information Modelling) process.

Complete Chapter List

Search this Book:
Reset