- Implementation of a Feed-Forward Neural Network model in JAVA for Intelligent Character Recognition.
- Working with the MNIST dataset.
- Preprocessing the data in MATLAB using various methods such as binarization, normalization, reduction and different types of transformations (edge detection, elastic distortions).
- Training the model with gradient descent optimization algorithm.
- 98.22% accuracy on the test set using 784-255-10 NN architecture.
-
Notifications
You must be signed in to change notification settings - Fork 0
MarijaStojchevska/ICR
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A Feed-forward Neural Network model in JAVA for Intelligent Character Recognition - trained and tested on the MNIST dataset. Classification accuracy up to 98.22%.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published