← 🤖 AI & Machine Learning

🔍 Interpretability Explorer

Prediction:
Top feature:
Explanation entropy: 0%
Gradient × Input attribution (backprop through the 6→8→8→2 net): φᵢ = xᵢ · ∂p/∂xᵢ, normalized so Σ|φᵢ| = 1
Drag — rotate · Scroll — zoom · Blue → gold edges trace each feature's path to the prediction

🔍 AI Interpretability Lab: Feature Attribution, Saliency & Attention Explorer

A live 6→8→8→2 neural network explains its own credit-approval decision in real time — switch between global feature importance, local gradient × input saliency, and an animated attention-style flow, then perturb the input to see the explanation change.

🔬 What It Demonstrates

Model interpretability is not one technique but a family of them. This simulation runs a real (small) neural network with an actual backpropagation pass, so the "Saliency" mode is a genuine gradient × input attribution — not a canned animation — while "Feature Importance" shows the simpler, global weight-based view that ignores the current input entirely. Watching both side by side makes the local-vs-global distinction concrete.

🎮 How to Use

Pick an explanation method, choose a feature to perturb and drag its value slider, or hit "New sample" for a fresh random input. Switch to "Attention Flow" to watch particles travel from the most-attributed input feature, through the hidden layers, to the predicted class. Drag to orbit the network and scroll to zoom.

💡 Did You Know?

"Gradient × Input" and its more robust cousins (Integrated Gradients, SHAP, LIME) are exactly how real interpretability tools explain production models — from credit scoring to medical diagnosis — and are increasingly required by regulations such as the EU's GDPR "right to explanation".