Digit_recognition-Machine-learning

A popular demonstration of the capability of machine learning techniques is object recognition in data processing.

Digit recognition system is the working of a machine to train itself or recognizing the digits from different sources. Developing such a system includes a machine to understand and classify the images of handwritten digits as 10 digits (0–9). The purpose of this project is to recognize the handwritten digits (0 to 9) from the famous MNIST dataset try to achieve near about 100% performance and near-human performance.

To execute this project :

1. Install anaconda navigator
2. download the repository as it is.
3. change the link of test and train file as the current location of your disk(where they are saved), inside the jupyter notebook
4. change the last line of the jupyter notebook to your folder where you want to save your final submission.
5. run all the command from the starting
6. A final submission.csv file will be created at last.