Learn AIWhat has the network learned?
Look inside learned features and find the shortcuts that can fool a model.
What you’ll explore
- Generalization
- Feature detectors
- Shortcut learning
- Causality
Your lessons
0 / 13 completeLearn the pattern, not the examples
A model can fit every training point and still fail on the next one. Find out how to tell.
What does this neuron notice?
Draw an image with 25 pixels, inspect each weight, and see what makes a detector respond.
Catch a model taking a shortcut
Change the background, keep the shape, and investigate what a perfect score was hiding.
Slide a detector across an image
Reuse one filter at many positions and trace how stride, borders and pooling change the result.
Teach useful invariances
Train on transformed images, check whether labels survive, and compare failure modes under a matched budget.
Compare convolution with image attention
Compare local filters with patch attention, then test which changes in image arrangement remain visible.
Turn sound into features
Connect samples, local frequency measurements and a spectrogram, then expose aliasing and window tradeoffs.
Order changes meaning
Train a small recurrent predictor, follow its hidden state and expose what a bag of events forgets.
Learn from relationships between examples
Train an encoder from paired views, diagnose collapsed features and test what a simple classifier can still recover.
Reuse a representation
Compare a new network with frozen and partly adapted features under matched target-label budgets.
Learn with objects and relationships
Train shared graph messages, change directed relationships and test whether reordering objects changes their predictions.
Locate and segment objects
Draw boxes and masks, expose merged and missed objects, and evaluate a tiny pixel classifier on real images.
Estimate depth and pose
Move paired cameras, reconstruct points and challenge pose estimates with wrong correspondences.