AEC Industry is traditionally a lazy adapter for new technologies. Nevertheless from ImageNet or Deep Learning to GANs and LLMs accessibility to AI for the non-expert user has exponentially grown over the last 5 years.
With a clear focus on a sustainable future for the human race-built environments, along with the content of the sessions, the student learn current usage and future trends for incorporating AI into workflows in the AEC.


Syllabus

Navarro-Mateu, D ‘An exercise on the evolving city’, Dec 2021

Learning will be devoted to the understanding of an up-to-date status of Narrow AI techniques. We will be devoted to provoking the understanding of the different types of problems weak AI domains tackle and their applicability within AEC. Special focus will be made on the capabilities of AI for analysis, design, planning, and management.

The sessions are grouped into approaches exploring different automation paradigms:

  • Statistical Learning + Optimization:
    • Markov Models + Uncertainty Management
    • Linear & logistic regression
    • Evolutionary Computation
    • Planning & approximate reasoning
  • Machine Learning:
    • Unsupervised processes & clustering
    • PCA, SOM + HBI
  • Supervised Decision Making:
    • ANNs, Lazy learning, Deep learning, GAN

The module’s outcomes are not just theoretical knowledge; they also focus on students’ analytical abilities through various case studies examined during the sessions. It is presented as a framework for developing methodologies to tackle unresolved AEC scenarios.

Learning Objectives

The course develops students’ critical thinking abilities, engaging them in debates that question different approaches and outcomes. Students critically reflect on a proposed framework, assessing the efficiency and suitability of AI methodologies for solving specific, existing AEC problems.

The course emphasizes developing short investigations that are both reflective and practical, producing conclusive outputs and fostering innovative visions for AI application in the AEC industry.


Faculty


Projects from this course

AI-Driven Inclusive Design: Topology Graph Analysis and NLP for Accessibility Solutions in Architecture

This project focuses on improving the accessibility and inclusivity of hospital environments for visually impaired individuals. Centered on Spain’s Primary Care Centres (CAPs), the initiative addresses critical navigation challenges faced by this community. By leveraging AI-driven tools, including topological graph analysis and semantic segmentation, the project provides architects with actionable insights to design healthcare spaces … Read more

Implementation of CNNs, SOMs and SVMs in post disaster analysis with drones

Introduction:The AI Theory class has provided us with comprehensive foundation in artificial intelligence, covering both fundamental principles and advanced methods. Through topics such as clustering, neural networks, evolutionary computing, and decision-making models, the course aims to equip students with the theoretical knowledge and practical insights needed to apply AI across various fields, including disaster management … Read more

Evolutionary Algorithm to Optimize Resource Allocation for Sustainable Solutions  

The problem we are addressing is the critical challenge of resource allocation for sustainable solutions in cities. Our focus is on how to meet environmental standards effectively by choosing efficient solutions while  staying within budget.The challenge cities face is resource allocation. Urban sustainability demands meeting environmental standards within tight and specific budgets. The task is … Read more

AI theory: Using NLP – Graph Rag for AI Suggestions in Facades, based on environmental guidelines

This project leverages Graph Retrieval-Augmented Generation (Graph RAG) to provide intelligent facades configuration recommendations aligned with the New European Bauhaus (NEB) principles. This post presents how we apply AI theory approaches for reaching the stablished target. The project correlates quantitative data and qualitative guidelines, by integrating 17% of the assessed metrics in this guidelines and creating … Read more