# Multi-script Handwritten Digit Recognition Using Multi-task Learning

arXiv: https://arxiv.org/abs/2106.08267 · HTML: https://mlsanity.com/paper/2106.08267/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 42 references that are in the map.
- First posted on arXiv 15 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Kannada-MNIST: A new handwritten digits dataset for the Kannada language](https://mlsanity.com/paper/1908.01242/) (2019)
- [Deep Learning Autoencoder Approach for Handwritten Arabic Digits Recognition](https://mlsanity.com/paper/1706.06720/) (2017)
- [MNIST-MIX: A Multi-language Handwritten Digit Recognition Dataset](https://mlsanity.com/paper/2004.03848/) (2020)
- [Handwritten Amharic Character Recognition Using a Convolutional Neural Network](https://mlsanity.com/paper/1909.12943/) (2019)
- [Handwritten Arabic Numeral Recognition using Deep Learning Neural Networks](https://mlsanity.com/paper/1702.04663/) (2017)
- [Handwritten and Machine printed OCR for Geez Numbers Using Artificial Neural Network](https://mlsanity.com/paper/1911.06845/) (2019)
- [Modified Segmentation Algorithm for Recognition of Older Geez Scripts Written on Vellum](https://mlsanity.com/paper/2006.00465/) (2020)

## Built on by (most cited first, 2 of 2)

- [Offline Handwritten Amharic Character Recognition Using Few-shot Learning](https://mlsanity.com/paper/2210.00275/) (2022)
- [Improving Amharic Handwritten Word Recognition Using Auxiliary Task](https://mlsanity.com/paper/2202.12687/) (2022)

## Abstract (arXiv)

Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it is not very common for multi-script digit recognition which encourage the development of robust and multipurpose systems. Additionally working on multi-script digit recognition enables multi-task learning, considering the script classification as a related task for instance. It is evident that multi-task learning improves model performance through inductive transfer using the information contained in related tasks. Therefore, in this study multi-script handwritten digit recognition using multi-task learning will be investigated. As a specific case of demonstrating the solution to the problem, Amharic handwritten character recognition will also be experimented. The handwritten digits of three scripts including Latin, Arabic and Kannada are studied to show that multi-task models with reformulation of the individual tasks have shown promising results. In this study a novel way of using the individual tasks predictions was proposed to help classification performance and regularize the different loss for the purpose of the main task. This finding has outperformed the baseline and the conventional multi-task learning models. More importantly, it avoided the need for weighting the different losses of the tasks, which is one of the challenges in multi-task learning.