### Bored of MNIST?

The goal of this competition is to provide a simple extension to the classic [MNIST competition](https://www.kaggle.com/c/digit-recognizer/) we're all familiar with. Instead of using Arabic numerals, it uses a recently-released dataset of Kannada digits.

Kannada is a language spoken predominantly by people of Karnataka in southwestern India. The language has roughly 45 million native speakers and is written using the Kannada script. [Wikipedia](https://en.wikipedia.org/wiki/Kannada)

![](https://storage.googleapis.com/kaggle-media/competitions/Kannada-MNIST/kannada.png)

This competition uses the same format as the [MNIST competition](https://www.kaggle.com/c/digit-recognizer/) in terms of how the data is structured, but it's different in that it is a synchronous re-run Kernels competition. You write your code in a Kaggle Notebook, and when you submit the results, your code is scored on both the public test set, as well as a private (unseen) test set.

### Technical Information

All details of the dataset curation has been captured in the paper titled: Prabhu, Vinay Uday. "Kannada-MNIST: A new handwritten digits dataset for the Kannada language." arXiv preprint [arXiv:1908.01242 (2019)](https://arxiv.org/abs/1908.01242)

The github repo of the author [can be found here](https://github.com/vinayprabhu/Kannada_MNIST).

On the [originally-posted dataset](https://www.kaggle.com/higgstachyon/kannada-mnist), the author suggests some interesting questions you may be interested in exploring. Please note, although this dataset has been released in full, the purpose of this competition is for practice, not to find the labels to submit a perfect score.

 In addition to the _main_ dataset, the author also disseminated an additional real world handwritten dataset (with 10k images), termed as the 'Dig-MNIST dataset' that can serve as an out-of-domain test dataset. It was created with the help of volunteers that were non-native users of the language, authored on a smaller sheet and scanned with different scanner settings compared to the _main_ dataset. This 'dig-MNIST' dataset serves as a more difficult test-set (An accuracy of 76.1% was reported in the paper cited above) and achieving ~98+% accuracy on this test dataset would be rather commendable.

### Acknowledgments
Kaggle thanks [Vinay Prabhu](https://www.kaggle.com/higgstachyon) for providing this interesting dataset for a Playground competition.

Image reference: https://www.researchgate.net/figure/speech-for-Kannada-numbers_fig2_313113588