Skip to content

Latest commit

 

History

History
6 lines (4 loc) · 309 Bytes

readme.md

File metadata and controls

6 lines (4 loc) · 309 Bytes

Digit Recognizer

Use a convolutional neural network to classify handwritten digits from the MNIST dataset. A variety of architectures and hyperparameters were tested, and the best model (submitted to Kaggle) used an ensemble of ResNet-type models. The accuracy on the test set for this model was 99.585%.