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%.
-
Notifications
You must be signed in to change notification settings - Fork 0
SeanScripts/digit-recognizer
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Recognize handwritten digits from the MNIST dataset
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published