State-of-the-Art Results with the Fashion-MNIST Dataset
Mukhamediev R.I.
October 2024Multidisciplinary Digital Publishing Institute (MDPI)
Mathematics
2024#12Issue 20
In September 2024, the Fashion-MNIST dataset will be 7 years old. Proposed as a replacement for the well-known MNIST dataset, it continues to be used to evaluate machine learning model architectures. This paper describes new results achieved with the Fashion-MNIST dataset using classical machine learning models and a relatively simple convolutional network. We present the state-of-the-art results obtained using the CNN-3-128 convolutional network and data augmentation. The developed CNN-3-128 model containing three convolutional layers achieved an accuracy of 99.65% in the Fashion-MNIST test image set. In addition, this paper presents the results of computational experiments demonstrating the dependence between the number of adjustable parameters of the convolutional network and the maximum acceptable classification quality, which allows us to optimise the computational cost of model training.
accuracy , convolution neural networks , Fashion-MNIST
Text of the article Перейти на текст статьи
Institute of Automation and Information Technologies, Satbayev University (KazNRTU), 22 Satpayev Street, Almaty, 050013, Kazakhstan
Institute of Information and Computational Technologies, CS MSHE RK (Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan), 28 Shevchenko Street, Almaty, 050010, Kazakhstan
Institute of Automation and Information Technologies
Institute of Information and Computational Technologies
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026