The dataset is the subset of nepali handwritten digit from :
@inproceedings{acharya2015deep, title={Deep learning based large scale handwritten Devanagari character recognition}, author={Acharya, Shailesh and Pant, Ashok Kumar and Gyawali, Prashnna Kumar}, booktitle={Software, Knowledge, Information Management and Applications (SKIMA), 2015 9th International Conference on}, pages={1--6}, year={2015}, organization={IEEE} }
I have trained it using MultiLayer Perceptron with 3 hidden layers (512x1024x512) and got 98.37% accuracy on test set.
Webapp is available at: https://aayush360.github.io/Nepali_Digit_Recognizer/