Your Cart
Loading
Only -1 left

Learn Machine Learning in Grasshopper - 3D Interactive Study Guide | 12-Step C# Script | Rhino 7/8

On Sale
$29.99
$29.99
Added to cart

+======================================================================+

| PAYHIP PRODUCT LISTING                       |

| Learn Machine Learning in Grasshopper                |

| 2026 Wickerson Studios                       |

+======================================================================+



------------------------------------------------------------------------

 TITLE

------------------------------------------------------------------------


Learn Machine Learning in Grasshopper - 3D Interactive Study Guide |

12-Step C# Script | Rhino 7/8



------------------------------------------------------------------------

 SUBTITLE / TAGLINE

------------------------------------------------------------------------


Data points scatter through 3D feature space. Regression lines thread

through point clouds. Decision boundaries slice the viewport. Neural

networks stack as node-and-wire diagrams. Gradient descent carves a

path down a loss landscape you can orbit. The foundations of ML for

computational designers - made visible, made understandable.



------------------------------------------------------------------------

 DESCRIPTION

------------------------------------------------------------------------


Machine learning is transforming design: surrogate models replace

slow simulations, generative algorithms explore design spaces, and

Bayesian optimisation guides parametric search. But what are these

tools actually doing?


This script makes it visible.


Drop a single C# component into Grasshopper, connect a slider (1-12),

and watch ML concepts come alive as 3D geometry you can orbit, zoom,

and bake into Rhino layers.


THE 12 STEPS:


Step 1 - Data & Features

 Samples scatter through 3D feature space as coloured spheres. Two

 classes separate into clusters. Normalisation diagram shows raw vs

 scaled data. Train/test split boxes. Distance rings show feature

 distances. 187 labels - the densest step in the series.


Step 2 - Linear Regression

 20 data points with a computed best-fit line (real regression, not

 faked). Residual error lines connect each point to the prediction.

 MSE loss box. Polynomial regression hint. Normal equation and

 gradient descent formulas. Mapped to Plane.FitPlaneToPoints().


Step 3 - Classification

 Two classes separated by a decision boundary line. Full sigmoid

 curve plotted point-by-point. Threshold annotation at 0.5.

 Multi-class softmax hint. Misclassified point marked. Linear

 separability concept explained.


Step 4 - K-Nearest Neighbours

 Query point surrounded by K=5 neighbourhood circle. Distance

 lines to all 5 neighbours. Vote tally showing class prediction.

 K choice guide (K=1 overfits, K=large underfits, use odd K).

 Distance metrics comparison. Voronoi = K=1 decision regions.


Step 5 - Decision Trees

 Full tree diagram: root node ("height > 10m?"), two internal

 nodes, four leaf predictions (PASS/FAIL). Entropy formula with

 purity explanation. Information gain. Decision regions shown as

 axis-aligned splits in feature space. Random forest note.


Step 6 - Neural Networks

 Full network diagram: 3 input nodes (area, height, glazing),

 two hidden layers of 5 nodes each, 2 output nodes (energy, cost).

 All connections drawn as wires. Forward pass and backpropagation

 arrows. Activation function reference (ReLU, Sigmoid, Tanh,

 Softmax). Weight annotation. Neuron equation.


Step 7 - Gradient Descent

 3D loss landscape as a wireframe paraboloid surface you can orbit.

 Gradient descent path of 8 steps from random start to minimum.

 Learning rate comparison: too small (crawls), just right (converges),

 too large (diverges). Axis labels (w1, w2, Loss). Update rule.

 Batch vs SGD vs mini-batch comparison.


Step 8 - Overfitting & Regularisation

 Three side-by-side diagrams: underfit (straight line), good fit

 (smooth curve), overfit (wiggly line through every point). Bias-

 variance tradeoff arrow from high bias to high variance. Sweet

 spot marker. Regularisation methods: L1/L2, dropout, early stopping,

 cross-validation.


Step 9 - Clustering (K-Means)

 36 points in 3 colour-coded clusters with computed centroids.

 Algorithm steps listed. Elbow method diagram with loss vs K curve

 and marked elbow point. K-means++ initialisation note. Inertia

 formula.


Step 10 - Dimensionality Reduction (PCA)

 30-point elliptical cloud with computed mean. PC1 arrow (max

 variance direction) and PC2 arrow (perpendicular, min variance).

 Projection lines dropping every point onto PC1. 1D projection

 shown below. Eigenvalue bar chart with explained variance

 percentages. Mapped to Plane.FitPlaneToPoints() = PCA!


Step 11 - Evaluation Metrics

 Large 4-cell confusion matrix with TP=42, FN=8, FP=5, TN=45.

 All metrics computed from the matrix: Accuracy 87%, Precision 89%,

 Recall 84%, F1 86%. Each metric annotated with plain-English

 meaning. Regression metrics: MSE, RMSE, MAE, R-squared.

 Precision-recall tradeoff note.


Step 12 - ML in Design

 Six-stage workflow pipeline (Parameters -> Simulate -> Collect Data

 -> Train Model -> Predict -> Optimise). Surrogate model diagram

 with speed annotation (ms vs hours). Generative design grid of

 varied forms. Bayesian optimisation acquisition function curve

 with "next sample" marker. Complete tools list.



KEY FEATURES:


 Single file - one C# script, paste and go

 12 interactive steps - slider-driven, instant 3D diagrams

 1,481 lines - comprehensive ML coverage

 187 annotated labels - highest density in the entire series

 8 colour-coded material branches - visual clarity

 Working algorithms - real regression computed in Step 2

 3D loss landscape - orbit gradient descent in Rhino

 Bake to layers - organised Rhino layers with TextDot labels

 Design context - every concept linked to architecture/engineering

 Zero plugins - just Rhino + Grasshopper

 Rhino 7 and 8 compatible (Windows and Mac)

 Code IS the textbook - read the source, learn the ML



------------------------------------------------------------------------

 TARGET AUDIENCE

------------------------------------------------------------------------


 Computational designers adding ML to their workflow

 Architecture students learning data-driven design

 Grasshopper users wanting to understand surrogate models

 Engineers exploring ML-guided optimisation

 Plugin developers building ML-powered tools

 Anyone learning ML who thinks visually

 Design professionals evaluating Hops/Python ML pipelines

 Researchers bridging parametric design and data science



------------------------------------------------------------------------

 TAGS / KEYWORDS

------------------------------------------------------------------------


machine learning, ML, neural network, regression, classification,

KNN, decision tree, random forest, gradient descent, overfitting,

regularisation, clustering, K-means, PCA, dimensionality reduction,

confusion matrix, precision, recall, F1, surrogate model, generative

design, Bayesian optimisation, Grasshopper, Rhino, C#, RhinoCommon,

parametric, computational design, data science, study guide, 3D,

scikit-learn, Hops, Python, deep learning



------------------------------------------------------------------------

 PRICING

------------------------------------------------------------------------


 Standalone                    $14.99


 Dual Bundle (ML + Linear Algebra)        $24.99

 Dual Bundle (ML + DSA)              $24.99

 Dual Bundle (ML + Comp Geometry)         $24.99


 Triple Bundle (ML + LinAlg + DSA)        $32.99


 Mega Bundle (all 11 scripts)           $79.99



------------------------------------------------------------------------

 SOCIAL MEDIA COPY

------------------------------------------------------------------------


 TWITTER / X (280 chars):

 Learn Machine Learning in Grasshopper 🧠 12 interactive 3D steps:

 regression, neural nets, gradient descent, clustering, PCA,

 evaluation. 187 labels, 1,481 lines. Single C# script. Zero

 plugins. ML for computational designers - decoded.


 INSTAGRAM / LINKEDIN:

 What actually happens inside a neural network?


 Data points scatter through 3D feature space. Regression lines

 thread through point clouds showing residual errors. Decision

 boundaries slice space into classification regions. Neural networks

 stack as node-and-wire diagrams with forward pass and backprop

 arrows. Gradient descent carves a path down a loss landscape you

 can orbit in Rhino.


 12 interactive steps. 1,481 lines. 187 annotated labels. One C#

 script. Zero plugins.


 Every concept mapped to a design application: surrogate models,

 generative design, Bayesian optimisation. The densest product in

 the series.


 Link in bio. #MachineLearning #Grasshopper #Rhino3D

 #ComputationalDesign #NeuralNetwork #DataScience #AI



------------------------------------------------------------------------

 THUMBNAIL SUGGESTIONS

------------------------------------------------------------------------


 1. Step 7 - 3D loss landscape with gradient descent path (most dramatic)

 2. Step 6 - Neural network node-and-wire diagram

 3. Step 1 - 3D feature space with coloured class clusters

 4. Step 11 - Confusion matrix with computed metrics



------------------------------------------------------------------------

 CROSS-SELL SUGGESTIONS

------------------------------------------------------------------------


 Learn Linear Algebra ($14.99) - vectors, matrices, transforms,

  the math behind every weight matrix and gradient computation

 Learn DSA ($14.99) - data structures powering ML pipelines

  (arrays, trees, hash maps, graphs)

 Learn Computational Geometry ($14.99) - spatial algorithms that

  combine with ML for geometric deep learning

 Learn Physics Simulation ($14.99) - the simulations ML surrogates

  replace (Kangaroo, particles, form-finding)

 Learn Structural Analysis ($14.99) - engineering simulations

  that benefit from ML surrogate modelling

 Learn Design Patterns ($14.99) - software architecture for

  building clean ML pipelines

 Learn C# ($14.99) - language fundamentals for RhinoCommon

 Learn Mesh Geometry ($14.99) - mesh data that feeds geometric ML

 Learn Python ($14.99) - the language of scikit-learn and PyTorch

 Learn Linux ($14.99) - server environments for ML training

 Chateau Elegance v11 ($29.99) - production Grasshopper tool



------------------------------------------------------------------------

 2026 Wickerson Studios - wickersonstudios.com

------------------------------------------------------------------------


You will get the following files:
  • GH (35KB)
  • PDF (30KB)
  • CS (71KB)
  • TXT (10KB)
  • TXT (5KB)