Syllabus: AI in Architectural Design: Introduction
Index
- 1. Course overview
- 2. Learning objectives
- 3. What we expect from you
- 4. What you can expect from the course team
- 5. Course structure
- 6. Resources, Tools & Browsers
- 7. Assessment & Certificate
- 8. A note about fraud
- 9.
License
1. Course overview
Course Overview: Exploring AI, Machine Learning, and Computer Vision in Architectural Design
This course is designed for architects, architectural students, and professionals eager to understand and integrate AI, machine learning, and computer vision into their design practices. It offers an introduction to this technology and the science, challenges, and ethics behind it. The course will help you navigate the complexities of the rapid developments in AI by giving you the starting skill sets to judge an AI product's technical and ethical features. The content of the course is designed to empower you with knowledge to choose among AI models effectively in your design practice and broaden your career and entrepreneurship opportunities in the context of AI in Architectural Design.
The course is designed in four modules, and each focuses on one of the important building blocks of AI: data, model, learning algorithm, and programming. The course starts focusing on theoretical and knowledge building through lectures, quizzes, peer-reviewed, and individual assignments, and moves to hands-on coding tutorials and assignments to comprehend the knowledge. The topics are revisited and practiced through different assignments to make sure that learning is long-lasting and effective.
Key Highlights of the Course:
-
Understanding AI and Machine Learning:
- Learn about the history and fundamentals of AI and machine learning, focusing on how these technologies serve as the scientific backbone of modern AI tools.
- Get familiar with various AI modalities and the building blocks of AI models, including learning algorithms, training, testing, and deployment processes.
-
Computer Vision and Its Applications:
- Delve into computer vision, known as the "eye of AI," and its applications within architectural design and engineering.
- Understand how computer vision can enhance design storytelling by enabling new forms of data visualization and interpretation.
-
Practical Skills Development:
- Gain hands-on experience in Python programming, the primary tool for implementing AI and machine learning models in architectural contexts.
- Practice machine learning with Python notebooks by working with architectural design datasets, focusing on both supervised and unsupervised learning methods.
-
Exploring Open-Source AI Tools and "Backstage" AI:
- Learn how to navigate the vast landscape of open-source AI tools and discover lesser-known "hidden gems" that can be used in architectural design projects.
- Understand the concept of "backstage" AI, which goes beyond mainstream AI products to provide more customized and license-free solutions.
-
Data-Driven Design Thinking:
- Develop a new methodology for scientific design thinking that integrates algorithmic approaches and data-driven insights.
- Learn to rethink design as data storytelling, leveraging AI to effectively transform and communicate design concepts.
No Prerequisites Required:
This introductory course requires no prior knowledge of AI, making it accessible to anyone interested in expanding their skill set to include AI and machine learning. Nevertheless, having programming skills eases the process.
Disclaimer: The course emphasizes using open-source AI models and resources. It focuses on introducing the basic blocks of AI, using Python programming frameworks rather than operating the pre-built AI applications/software.
2. Learning objectives
So, what will you learn in this course? At the end of this course, you will be able to:
- Explain machine learning as the science behind AI technology.
- Describe the role and importance of computer vision in AI and its application in architectural design.
- Recognize open-source AI models and datasets relevant to architectural practice.
- Develop Python programming skills to represent and reshape building data.
- Integrate AI techniques to visualize building data and enhance design narratives.
Note that each module and submodules have their own learning goals which contribute to the overall learning objectives of the course.
3. What we expect from you
We kindly ask you to read the learning objectives of the course before enrollment to make sure that it is aligned with your expectations from the course to avoid disappointment.
As an online learner, we expect you to be an active participant in this course by contributing to a positive atmosphere. We want you to question, share, and help others by engaging in meaningful discussions.
Regarding deadlines, we expect you to keep on track to benefit from learning within a community. This course is meant to be a place where you learn with and from others. In this sense, we would like you to experience collaboration and peer feedback, so please make sure you follow along with other participants to enrich the overall learning experience.
You are expected to follow discussion and collaboration guidelines. Respect the course policies, academic integrity, and most importantly, the instructors and other learners.
Some assignments are open-ended, encouraging creativity and research to apply design thinking. You are expected to actively engage with these tasks and contribute meaningful solutions to deliver high-quality work.
4. What you can expect from the course team
The moderator will guide you throughout the course, launching the biweekly content, promoting and engaging in discussions, and providing general feedback. Guidance and support will happen regularly.
Please use the forum for your questions for more efficient communication. The teaching team will be available in the forum at least twice a day to answer your questions.
Response Time: We will respond to all your questions and posts within 24-48 hours. If this is not possible for any reason, we will let you know.
You will receive feedback on your graded assignment within 72 hours of the submission deadline. After receiving your grade and feedback, you will have 48 hours to revise and resubmit the assignment if needed. No additional feedback will be provided after the resubmission, but your grade will be updated if there is an improvement.
5. Course structure
The course is organized into 4 modules.
In the Getting Started section, you’ll get to know the course structure, get familiarized with the virtual learning environment, complete your profile, meet your fellow students, and the moderators. These introductory tasks should be completed
There are 4 modules in the course. Modules include video lectures, quiz questions, coding tutorials, and some assignments. We encourage you to interact with your fellow learners on the discussion forums and ask your moderators any relevant questions.
- Module 1: AI Knowledge: Part 1
- Module 2: AI Knowledge: Part 2
- Module 3: Comprehension - Part 1
- Module 4: Comprehension - Part 2
Module 1: AI Knowledge - Part 1
History of artificial intelligence, Building blocks of AI, Data, and ethics, AI applications in architectural design.
-
- AI definition
- Machine learning
- Data Society
- DIKW pyramid
- Data technicalities
- AI modalities
Module 2: AI Knowledge - Part 2
Building AI, understanding models, learning algorithms, and the AI development process, introduction to Python.
-
- Building AI
- Model
- Learning algorithms
- Topological data
- Unsupervised learning
Module 3: Comprehension - Part 1
Hands-on AI projects for data visualization, unsupervised learning, and floor plan data using customized AI models.
-
- Introduction to Python
- Image Data
- Computer Vision
Module 4: Comprehension - Part 2
Supervised learning, foundation models, and hands-on AI projects for building energy classification.
-
- Foundation models
- Supervised learning project
Wrap-up
6. Resources, Tools & Browsers
All educational resources will be available in the course. They consist of short videos and readings to support you in the completion of the biweekly learning activities.
External materials are provided from an educational YouTube channel of AIBlocks.
Moreover, we provide optional extra learning material for interested students. Resources are books, ebooks, articles, webpages, etc.
We support the following browsers: Chrome, Firefox, and Safari.
7. Assessment & Certificate
Only verified participants have access to graded assignments. To complete the course you will need to score 70%. All assignments are mandatory. Assessment criteria for the assignments are detailed in the course. Verified participants can check their scores at any time under the course’s Progress page.
| MODULE 1 | MODULE 2 | MODULE 3 | MODULE 4 |
| Quiz = 10 % | Quiz = 10 % | Quiz = 10 % | Quiz = 0 % |
| Vocareum = 0 % | Vocareum = 0 % | Vocareum = 15 % | Vocareum = 25 % |
| Assignment = 15 % | Assignment = 15 % | Assignment = 0 % | Assignment = 0 % |
Upgrade to a Verified Certificate gives you:
- a certificate if you completed the course;
- access to graded assignments;
- access to the archived course after the end date.
These certificates will indicate you have completed the course, but will not include a specific grade. Certificates will be issued by edX under the name of DelftX, designating the institution from which the course originated.
Do you need financial assistance? edX offers a discount on our verified certificates to learners who cannot afford to pay full price. Check the edX support page for financial assistance.
Generating an ID-verified certificate
Verified certificates will be issued a few days after the end of the course to verified participants who successfully completed the course. Certificates can be downloaded from your Student Dashboard (look for the Download button next to the name of our course). An ID-verified Certificate of Achievement is available for the amount specified on the course home page. You can upgrade on your edX Dashboard to Verified during the course. Once produced, a certificate cannot be reissued; hence, you must verify the way in which your name appears. Check that, in your edx.org account, your name is correctly spelled, since it will appear on the final certificate.
8. A note about fraud
Plagiarism is a violation of copyright as it involves reproducing (parts of) another person’s work without stating the source, and thereby failing to comply with an essential aspect of copyright. This includes images, calculations, answers, and the use of AI-generated content, unless clearly acknowledged and referenced. Intentional plagiarism constitutes a transgression within the academic world. In many cases, plagiarism is unintentional, negligence, or simply poor source acknowledgement, but do take care to give all authors credit or ask for assistance if required.
In this course, you are allowed to use AI tools to assist you with language, searching content, and coding. Where possible, indicate that the work is AI-generated.
Whenever you reference content from a source, you need to cite it correctly. For further details on how and when to cite sources, see the TU Delft Library's website.
Please note that you are expected to follow the Learning and Assessment Regulations of the TU Delft Extension School for Continuing Education.
9. License
Delft University of Technology holds the copyright to all DelftX courses, including AI in Architectural Design: Introduction. Unless otherwise stated, the course materials of this MOOC are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License. For licensing purposes, "course materials" are defined as the syllabus, learning objectives, unit descriptions and explanations, videos, and the framing text that accompanies resources curated from third parties. That excludes the third-party resources themselves, forum discussions, quizzes, exercises, and all forms of assessment.