Grasshopper Plug-Ins for Machine Learning
-
Intro
-
Plug-In Overview
-
ML abilities overview
Information
| Last updated | November 14, 2024 |
| Primary category | |
| Secondary category |
Responsible
| Faculty |
Grasshopper Plug-Ins for Machine Learning 0/2
Grasshopper Plug-Ins for Machine Learning
An overview of the different plug-ins that allow you to integrate machine learning techniques into your Grasshopper workflows.
In this guide, we present plug-ins that allow you to integrate machine learning techniques into your Grasshopper workflows. Doing so enables you to analyze, predict, and optimize designs and helps with analysis and optimization. This page presents and overview of the different plug-ins that are available for you followed by tutorials organized under general themes.
Grasshopper Plug-Ins for Machine Learning 1/2
Plug-In Overview
Currently there are four plug-ins that can be used for Machine Learning (ML) inside Grasshopper:
- PUG
- Lunchbox
- Dodo
- Owl
Dodo
Dodo is a collection of tools for machine learning, optimization, and geometry manipulation. You can find more information on Food4Rhino: Dodo | Food4Rhino
Lunchbox
LunchBox is a plug-in for Grasshopper for exploring mathematical shapes, paneling, structures, and data management. You can find more information on Food4Rhino: LunchBox | Food4Rhino
Owl
Owl is a library written for machine learning-oriented data processing. You can find more information on Food4Rhino: Owl | Food4Rhino
Pug
Pug implements the Machine Learning library Tensorflow.NET in Grasshopper to provide some Machine Learning functionalities in Grasshopper. You can find more information on Food4Rhino: Pug | Food4Rhino
Grasshopper Plug-Ins for Machine Learning 2/2
ML abilities overview
The tables below gives an overview of for which ML algorithm which plug-in can be used. You can also find more information through this article on Medium: Grasshopper Meets AI. Remaining in the familiar territory | by Fatemeh Mostafavi | Medium
Supervised Learning
|
Plug-In or Software |
Regression Methods | Bayes Classifiers | K-Nearest Neighbours | Decision Trees | Support Vector Machines |
| Dodo (GH) | X | X | |||
|
Lunchbox (GH) |
X | X | X | X | |
| Owl (GH) | |||||
| Pug (GH) | X | X | |||
| ModeFRONTIER | X |
Unsupervised Learning
| Plug-In or Software | Gaussian Mixtures | Self-Organizing Maps | K-Means | Spectral Clustering | Generative Models |
| Dodo (GH) | X | ||||
| Lunchbox (GH) | X | X | X | ||
| Owl (GH) | X | ||||
| Pug (GH) | |||||
| ModeFRONTIER | X |
Reinforcement Learning
| Plug-In or Software | Value Iteration | Policy Iteration | Q-Learning |
| Dodo (GH) | |||
| Lunchbox (GH) | |||
| Owl (GH) | X | X | X |
| Pug (GH) | X | X | X |
| ModeFRONTIER |