Unsupervised Deep Learning in Character Recognition
The recognition of handwritten digits is a well-researched problem and has many applications in real life. The important applications include automatic reading of addresses on postal envelopes, automated form processing, automated processing of handwritten bank cheques, and filled-in forms like questionnaires or money orders. Digit recognition serves as an evaluation task because the problem is well defined and benchmark datasets are easily available.
- LeCun, Y., Bottou, L., Orr, G.B., Müller, K.R.: Efficient backprop. In: Neural networks: tricks of the trade, pp. 9–50. Springer, Berlin, Heidelberg (1998)Google Scholar
- Nawi, N.M., Hamid, N.A., Ransing, R.S., Ghazali, R., Salleh, M.N.M.: Enhancing back propagation neural network algorithm with adaptive gain on classification problems. Int. J. Database Theory Appl. 4(2) (2011)Google Scholar
- Wang, S., Manning, C.: Fast dropout training. In: International Conference on Machine Learning, pp. 118–126 (2013, Feb)Google Scholar
- Wani, M.A., Afzal, S.: Gain parameter and dropout-based fine tuning of deep networks. Int. J. Intell. Inf. Database Syst. 11(4), 236–254 (2018b)Google Scholar