Hand-Drawn Digit Classifier
Train a tiny neural network in the browser to recognise digits you draw with a mouse.
Start building ↓The build
Load the data
Pull in labelled 28×28 digit images.
Define the model
Stack input, hidden and a 10-way softmax output.
Train it
Run a few epochs and watch accuracy climb past 95%.
Draw & predict
Sketch a number and let the model name it.
The network learns patterns of pixels for each digit during training, then matches your drawing to the most similar learned pattern.
A closer look
Training nudges thousands of weights via gradient descent until outputs match labels; softmax turns scores into probabilities.
Variables to test
- 1 Shrink the hidden layer — how few neurons still hit 90%?
- 2 Feed messy digits — where does it confidently fail?
More AI
Rock-Paper-Scissors Vision
Use a webcam and a no-code model to recognise your hand and play rock-paper-scissors.
Spam Email Classifier
Train a model on example messages so it can flag new ones as spam or not.
Sentiment Analyzer
Feed in movie reviews and the model tells you whether each one is positive or negative.