051-0726-16L Creative Data Mining. Intuitively Analysing Design Ideas
Semester | Frühjahrssemester 2016 |
Dozierende | G. Schmitt |
Periodizität | jedes Semester wiederkehrende Veranstaltung |
Lehrsprache | Englisch |
Kurzbeschreibung | This course will shed some light on what to gain by using state-of-the art data mining techniques in architectural design and planning. |
Lernziel | The participants of this course learn how to use modern data mining methods in order to work with quantifiable qualities in architectural planning in a drastically more efficient manner. This is done by focusing on the connection between sketching on paper and interpreting those sketches with the aid of ready to use machine learning tools. The goal of the course is to provide the knowledge needed in order to use data mining methods for placing architectural projects on a firmer foundation. |
Inhalt | The course is focusing on creating deeper insights in design tasks, as well as gaining a better overview over design alternatives for planning projects. Additionally there are two kinds of non-architectural skills the participants can develop during this course: On the one hand, practical examples will help to understand how clustering methods like PCA, Self-Organizing Maps or K-Means could be applied for architecture. On the other hand, by a short overview on how to successfully copy and paste code-snippets to customize the computational tools presented the students are introduced to coding. Starting with compact introductions for generative design methods, the course is leading through a set of examples out of the field of architecture, each built on one another. Every one of those examples helps explaining how to apply ready-to-use computational design and analysis methods on certain steps of planning processes, which designers face in their everyday life. |
Skript | Additional information may be found under the following link: Link Please feel free to get in contact with our team by sending an email to Matthias Standfest Link |
Literatur | Further Information Link |
Voraussetzungen / Besonderes | For this course no prior coding experience is required. |