@article{ART003120902},
author={Seungbin Lee and Jungsoo Rhee},
title={Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2024},
volume={29},
number={9},
pages={1-7},
doi={10.9708/jksci.2024.29.09.001}
TY - JOUR
AU - Seungbin Lee
AU - Jungsoo Rhee
TI - Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization
JO - Journal of The Korea Society of Computer and Information
PY - 2024
VL - 29
IS - 9
PB - The Korean Society Of Computer And Information
SP - 1
EP - 7
SN - 1598-849X
AB - In this paper, we proposes a Convolutional Neural Networks(CNN) equipped with Batch Normalization(BN) for handwritten digit recognition training the MNIST dataset. Aiming to surpass the performance of LeNet-5 by LeCun et al., a 6-layer neural network was designed. The proposed model processes 28x28 pixel images through convolution, Max Pooling, and Fully connected layers, with the batch normalization to improve learning stability and performance. The experiment utilized 60,000 training images and 10,000 test images, applying the Momentum optimization algorithm. The model configuration used 30 filters with a 5x5 filter size, padding 0, stride 1, and ReLU as activation function. The training process was set with a mini-batch size of 100, 20 epochs in total, and a learning rate of 0.1. As a result, the proposed model achieved a test accuracy of 99.22%, surpassing LeNet-5's 99.05%, and recorded an F1-score of 0.9919, demonstrating the model's performance. Moreover, the 6-layer model proposed in this paper emphasizes model efficiency with a simpler structure compared to LeCun et al.'s LeNet-5 (7-layer model) and the model proposed by Ji, Chun and Kim (10-layer model). The results of this study show potential for application in real industrial applications such as AI vision inspection systems.
It is expected to be effectively applied in smart factories, particularly in determining the defective status of parts.
KW - MNIST dataset;Batch Normalization;Max Pooling;Fully connected layers;CNN;LeNet-5
DO - 10.9708/jksci.2024.29.09.001
ER -
Seungbin Lee and Jungsoo Rhee. (2024). Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization. Journal of The Korea Society of Computer and Information, 29(9), 1-7.
Seungbin Lee and Jungsoo Rhee. 2024, "Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization", Journal of The Korea Society of Computer and Information, vol.29, no.9 pp.1-7. Available from: doi:10.9708/jksci.2024.29.09.001
Seungbin Lee, Jungsoo Rhee "Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization" Journal of The Korea Society of Computer and Information 29.9 pp.1-7 (2024) : 1.
Seungbin Lee, Jungsoo Rhee. Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization. 2024; 29(9), 1-7. Available from: doi:10.9708/jksci.2024.29.09.001
Seungbin Lee and Jungsoo Rhee. "Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization" Journal of The Korea Society of Computer and Information 29, no.9 (2024) : 1-7.doi: 10.9708/jksci.2024.29.09.001
Seungbin Lee; Jungsoo Rhee. Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization. Journal of The Korea Society of Computer and Information, 29(9), 1-7. doi: 10.9708/jksci.2024.29.09.001
Seungbin Lee; Jungsoo Rhee. Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization. Journal of The Korea Society of Computer and Information. 2024; 29(9) 1-7. doi: 10.9708/jksci.2024.29.09.001
Seungbin Lee, Jungsoo Rhee. Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization. 2024; 29(9), 1-7. Available from: doi:10.9708/jksci.2024.29.09.001
Seungbin Lee and Jungsoo Rhee. "Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization" Journal of The Korea Society of Computer and Information 29, no.9 (2024) : 1-7.doi: 10.9708/jksci.2024.29.09.001
