Home▸Machine Learning & Neural Networks▸GAN: Generator vs Discriminator Explained

🎭 GAN: Generator vs Discriminator Explained

Interactive 3D visualization of GAN training where a generator's fake point cloud gradually morphs to match a real data manifold while a discriminator's decision boundary reshapes each epoch to keep telling them apart.

Machine Learning & Neural Networks3DModerate60 FPS

The scene shows a blue point cloud forming a fixed real-data ring manifold and an amber point cloud representing generator samples that start scattered and, epoch by epoch, morph toward matching the ring, while a translucent grid surface representing the discriminator's decision boundary reshapes itself around the shifting fake cloud.

🔬 What It Demonstrates

🎮 How to Use

Pick a training mode from the dropdown, use the speed slider to control how fast epochs advance, and press Play/Pause or Rebuild to restart the run from a freshly scrambled generator state.

💡 Did You Know?

The original 2014 GAN paper by Ian Goodfellow was reportedly conceived after a late-night bar conversation about whether a network could learn to generate data purely by competing against another network trying to catch it faking.

⚙ Under the hood

gangenerative-adversarial-networksdiscriminatorgeneratordeep-learningmachine-learning

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install