Deep Learning Approach for Digit Recognition using the MNIST Dataset
Keywords:
Deep Learning, Convolutional Neural Networks (CNNs), Digit Recognition, MNIST Dataset, Computer Vision, Image Classification, Data PreprocessingAbstract
Digit identification has been a crucial function in computer systems with widespread implementations in different domains, for eg. image processing & handwriting recognition. Deep machine learning methods that have been used, especially CNNs, have displayed remarkable outcomes in digit identification. In our research paper, we presented a CNN-based approach for digit recognition using the MNIST dataset, which is a typical point of reference dataset for this task. MNIST comprises Seventy Thousand grayscale images of handwritten digits of pixel size 28 x 28.
We have implemented and trained our model using the TensorFlow and Keras libraries. Our approach achieved an accuracy of 99.10% on the test set, indicating its effectiveness.
Downloads
References
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
Simard, P. Y., Steinkraus, D., & Platt, J. C. (2003). Best practices for convolutional neural networks applied to visual document analysis. International Conference on Document Analysis and Recognition, 958-962.
Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504-507.
Cireşan, D. C., Meier, U., Gambardella, L. M., & Schmidhuber, J. (2012). Deep, big, simple neural nets for handwritten digit recognition. Neural computation, 24(8), 2227-2230.
Lecun, Y., Cortes, C., & Burges, C. (2010). MNIST handwritten digit database. AT&T Labs [Online]. Available: http://yann.lecun.com/exdb/mnist/.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929-1958.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2017). Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530.
