# Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)

arXiv: https://arxiv.org/abs/1811.08278 · HTML: https://mlsanity.com/paper/1811.08278/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Comprehensive Survey of Model Compression and Speed up for Vision Transformers](https://mlsanity.com/paper/2404.10407/) (2024)
- [Scanflow: A multi-graph framework for Machine Learning workflow management, supervision, and debugging](https://mlsanity.com/paper/2111.03003/) (2021)
- [Learning from the Tangram to Solve Mini Visual Tasks](https://mlsanity.com/paper/2112.06113/) (2021)
- [Overhead-MNIST: Machine Learning Baselines for Image Classification](https://mlsanity.com/paper/2107.00436/) (2021)
- [A contextual analysis of multi-layer perceptron models in classifying hand-written digits and letters: limited resources](https://mlsanity.com/paper/2107.01782/) (2021)
- [Mixing Deep Learning and Multiple Criteria Optimization: An Application to Distributed Learning with Multiple Datasets](https://mlsanity.com/paper/2112.01358/) (2021)
- [Human-in-the-loop online multi-agent approach to increase trustworthiness in ML models through trust scores and data augmentation](https://mlsanity.com/paper/2204.14255/) (2022)
- [Standardness Clouds Meaning: A Position Regarding the Informed Usage of Standard Datasets](https://mlsanity.com/paper/2406.13552/) (2024)

## Abstract (arXiv)

Although the image recognition has been a research topic for many years, many researchers still have a keen interest in it[1]. In some papers[2][3][4], however, there is a tendency to compare models only on one or two datasets, either because of time restraints or because the model is tailored to a specific task. Accordingly, it is hard to understand how well a certain model generalizes across image recognition field[6]. In this paper, we compare four neural networks on MNIST dataset[5] with different division. Among them, three are Convolutional Neural Networks (CNN)[7], Deep Residual Network (ResNet)[2] and Dense Convolutional Network (DenseNet)[3] respectively, and the other is our improvement on CNN baseline through introducing Capsule Network (CapsNet)[1] to image recognition area. We show that the previous models despite do a quite good job in this area, our retrofitting can be applied to get a better performance. The result obtained by CapsNet is an accuracy rate of 99.75%, and it is the best result published so far. Another inspiring result is that CapsNet only needs a small amount of data to get excellent performance. Finally, we will apply CapsNet's ability to generalize in other image recognition field in the future.