I implemented this Hand Written Digit Recognition System by three layers neural networks. Each layer contains one bias node to adjust my training and they are all fully connected to the next layer. The values produced by forward propagation, but the node coefficients are update by backward propagation. After trained by 60000 images, the model performs a 95% accuracy on 10000 testing images.
wning0101/hand_write_digit_recognition_NN
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
using neural network to recognize hand write digit
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published