Home▸Networks & Graph Theory▸Optimizer Race: SGD vs Momentum vs Adam on a Small Neural Network

🧪 Optimizer Race: SGD vs Momentum vs Adam on a Small Neural Network

Train the same small neural network three ways at once, from identical starting weights and identical mini-batches: plain SGD, momentum and Adam. Watch each decision boundary form on 2D datasets, compare loss curves and test accuracy, and verify backpropagation against finite differences.

Networks & Graph Theory2DModerate60 FPS📱 Mobile-adapted⇄ 3D version
Optimizer Race: SGD vs Momentum vs Adam on a Small Neural Network ↗ Open standalone
⚙ Under the hood

Train the same small neural network three ways at once, from identical starting weights and identical mini-batches: plain SGD, momentum and Adam. Watch each decision boundary form on 2D datasets, compare loss curves and test accuracy, and verify backpropagation against finite differences.

Neural NetworksOptimizersBackpropagationAdamDecision BoundaryAI Algorithms

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)