A Threshold Is a Decision
Keep the model. Change the rule. See who gets a different decision and what those mistakes cost.
Explore the labVISUAL LEARNING
Move one thing.
Understand more.
Small experiments that make a big idea visible. Change a threshold, move a centroid, explore a ResNet or fine-tune a network, and follow what happens.
13 interactive labsNo installationPython inside
A QUESTION WORTH EXPLORINGWhat makes a group
What makes a group
a group?
Start with the points. Choose the centers. See why the answer depends on the question.
Explore K-meansTHE LAB COLLECTION
Try it. Change it.
Explain what you see.
Built for curiosity, classroom demonstrations and a closer look at the code behind an idea.
13 labs
ROC & Precision–Recall Explorer
Connect a moving threshold to the confusion matrix, ROC space and the precision–recall curve.
Explore the labBuild a Decision Tree
Sort a basket of fruit using features you can see. Compare splits and discover why depth matters.
Explore the labK-Means: Find the Groups
Place the centers, assign the points and update the means. Watch the groups emerge one step at a time.
Explore the labDraw the Best-Fit Line
Move a line, inspect its residuals and reveal the least-squares solution. Add an outlier and compare the errors.
Explore the labFit or Overfit?
Turn up model complexity and compare training with held-out validation. Find where extra flexibility stops helping.
Explore the labBuild a Human–AI Team
Compare human and AI decisions, full review and selective review. Spend a review budget where it can help.
Explore the labBuild a Filter
Edit a kernel and see what it does to an image. Inspect one neighborhood to understand every multiply and add.
Explore the labNeural Network Parameter Explorer
Build an MLP or CNN. Change its layers and follow every weight, bias, output shape and trainable parameter.
Explore the labTransfer Learning: Choose What Learns
Freeze a real ResNet, choose the fine-tuning depth and see every trainable parameter. Turn your choices into PyTorch code.
Explore the labResNet: Inside the Residual Block
Open the stages of ResNet-18, 34 and 50. Follow tensor shapes, compare shortcuts and make the residual addition visible.
Explore the labData Augmentation: Build the Variations
Transform an image, generate a repeatable batch and inspect each crop, rotation and color adjustment. Decide what should stay invariant.
Explore the labRegularization: Learn Beyond the Sample
Train paired neural networks in your browser. Compare measured learning curves, validation errors and the predictions that remain.
Explore the labNo labs match this combination. Try another topic or course.
HOW TO USE A LAB
One idea.
Four ways in.
01
Understand
Begin with one clear question and make a prediction.
02
Explore
Change the controls and connect the visual result to the decision.
03
See the code
Open a short Python implementation and connect it to the experiment.
04
Try it
Use the prompts to explain, compare or design a new example.