Short··0:10
Watch a Neural Network Learn in 10 Seconds
About this video
Neural network learning, visualized: 72 dots, 205 parameters, and 32 mistakes falling to zero. Watch the decision boundary bend as gradient descent updates the network.
Blue dots belong in blue. Pink dots belong in pink. White rings mark wrong predictions.
This is a time-compressed replay of real training with Andrej Karpathy's micrograd, with smooth interpolation between updates. The final 72/72 score is on the training examples; unseen data is the real test.
Open-source neural network library: github.com/karpathy/micrograd
Topics
neural networkmachine learningneural network visualizationgradient descentmicrogradbackpropagationcomputer scienceAI visualizationdeep learningdecision boundary
