Home▸AI & Machine Learning▸Model Compression Techniques Explained

🗜️ Model Compression Techniques Explained

A 3D neural network you can prune, quantize and distil in real time — watch weak connections vanish, weight precision collapse into color bands, and a compact student network absorb a teacher's knowledge.

AI & Machine Learning3DAdvanced60 FPS

An interactive 3D neural network that you compress live — prune away weak connections by magnitude, quantize the survivors into a shrinking ladder of bit-widths, and switch on knowledge distillation to watch a compact student network absorb the teacher's behaviour.

🔬 What It Demonstrates

Edges are globally sorted by weight magnitude, so raising the pruning slider strips the weakest connections first — exactly how real magnitude pruning works. Lowering the quantization bit-width rounds every surviving weight onto a coarser ladder of values, visible as color banding on the connections.

🎮 How to Use

Pick a network size, then drag the pruning and quantization sliders and watch the model size, inference speed-up and estimated accuracy update live. Toggle distillation to reveal a small student network being fed synthetic "knowledge" particles from the teacher's output layer.

💡 Did You Know?

Production compression pipelines usually stack these techniques: a pruned, 8-bit quantized, distilled model can be 10-20× smaller than its full-precision teacher while retaining most of its accuracy, which is how large models end up running on phones and microcontrollers.

⚙ Under the hood

artificial intelligencemachine learningneural networksmodel compressionquantizationpruningThree.js

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