← 📊 Machine Learning & Neural Networks

📊 Batch Normalization: Taming Internal Covariate Shift

Step: 0
Loss:
Drag — rotate · Scroll — zoom

📊 Batch Normalization: Taming Internal Covariate Shift

The simulation visualises activation distributions flowing through a multi-layer network in 3D, contrasting the drifting, spread-out distributions of unnormalized training with the stable, tightly clustered distributions produced when batch normalization is applied.

🔬 What It Demonstrates

The simulation visualises activation distributions flowing through a multi-layer network in 3D, contrasting the drifting, spread-out distributions of unnormalized training with the stable, tightly clustered distributions produced when batch normalization is applied.

🎮 How to Use

Toggle batch normalization on or off to compare training behaviour, use the speed slider to control how fast training steps play out, and use play/pause and rebuild to restart the network with fresh random weights.

💡 Did You Know?

The original 2015 batch normalization paper allowed one image classification model to match its previous accuracy using 14 times fewer training steps, while also beating the original network's best accuracy outright.