AI / ML VisualizerRuns in your browser · No API keyOpen Model
← All topics

Training & Optimization

Gradient Descent

Follow actual optimization steps across a loss landscape.

Optimization trajectory · x and y parametersOptimization trajectory · x and y parameters-4-4-2-2002244Batch GDAdam comparisonPoint 1: (2, 1.5), class 0
L = x² + 3y²Position (2, 1.5); loss 10.75
Step 0 / 100
Calculated loss historyCalculated loss history000.252.68750.55.3750.758.0625110.75Loss

Continue exploring

Optimizer Comparison →Vanishing & Exploding Gradients →Weight Initialization →

No account required. Local images and model files stay in your browser. Educational models demonstrate mechanisms; they are not production predictors.