Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176897,
        author = {Sarthak Sahu and Prof.Vikram Rajpoot},
        title = {Dataset Digit Recognization Using CNN For Enhanced Accuracy On MNIST},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {8102-8105},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176897},
        abstract = {This research delves into the implementation of Convolutional Neural Networks (CNNs) for the task of handwritten digit recognition using the MNIST dataset. The objective was to design and optimize a CNN-based model to surpass the performance of traditional machine learning methods and earlier CNN architectures. The final deep learning model, constructed using TensorFlow and Keras, achieved an accuracy exceeding 99% on the test dataset. The study demonstrates the importance of architectural design choices, including convolutional layers, pooling layers, batch normalization, dropout, and ReLU activation functions in enhancing model generalization and reducing overfitting. The results validate the efficacy of the enhanced CNN and suggest its applicability in real-world digit recognition systems.},
        keywords = {Convolutional Neural Network, MNIST, Handwritten Digit Recognition, Deep Learning, Image Classification},
        month = {May},
        }