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

TL;DR

This paper compares four neural network models on the MNIST handwritten digit dataset, highlighting that the CapsNet model achieves the highest accuracy of 99.75% with less data, demonstrating its superior generalization ability.

Contribution

The paper introduces an improved CapsNet model for image recognition and demonstrates its superior performance over traditional CNN, ResNet, and DenseNet models on MNIST.

Findings

CapsNet achieves 99.75% accuracy on MNIST.

CapsNet requires less data to perform well.

CapsNet outperforms other models in accuracy.

Abstract

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.