From the course: Grasshopper: Generative Design for Architecture
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Classification
From the course: Grasshopper: Generative Design for Architecture
Classification
- [Instructor] Classification algorithms, particularly neural networks, are often the first techniques you think of when considering machine learning. Many of the most powerful applications of machine learning are classification systems. Things like text recognition, speech recognition, or facial recognition. Neural networks based on the layered architecture of biological brains have emerged as a common classification technique because they are able to group explicit, visible features into abstract or inferred features that correlate closely to the pre-defined classes in the training data. Let's look at an example of how this works. I have the exercise file open already. If I look at the Rhino preview I see a box shaped cloud of points. This point cloud represents a bad point cloud scan. Because there are points inside of the box. If I look in Grasshopper I see I have my bad point cloud scan importing. But I have a bunch of training data. This training data are lots and lots of points…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.