Home▸AI & Machine Learning▸Neural Architecture Search Simulation

🧪 Neural Architecture Search Simulation

Watch DARTS-style differentiable neural architecture search converge: a candidate cell graph relaxes each edge into a softmax mixture over operations, gradient descent sharpens it toward a discrete architecture, and you control the learning rate, accuracy/efficiency trade-off and temperature annealing.

AI & Machine Learning2DModerate60 FPS📱 Mobile-adapted

This simulation investigates the DARTS technique for automatically designing neural network architectures: a small cell graph — two input nodes and two intermediate nodes joined by five candidate edges — starts with every edge holding a soft mixture over four operations (none, skip-connection, 3×3 convolution, 5×5 convolution). Each training step runs one analytic gradient-descent update on the mixture weights, pulled toward whichever operations best trade off accuracy against compute cost under your chosen efficiency weight, while a decaying softmax temperature sharpens the blend into a single discrete architecture — the exact continuous-relaxation trick real automated machine learning pipelines use to search architecture space with ordinary backpropagation instead of training thousands of candidates from scratch.

⚙ Under the hood

This simulation investigates techniques for automatically designing and optimizing neural network architectures. It explores algorithms that search for the best structure for a given task.

Neural ArchitectureSearch AlgorithmAI

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