Automatic Recognition of Handwritten Digits Using Multi-Layer Sigmoid Neural Network
Journal: International Journal of Science and Research (IJSR) (Vol.5, No. 3)Publication Date: 2016-03-05
Authors : Said Kassim Katungunya; Xuewen Ding; Juma Joram Mashenene;
Page : 951-955
Keywords : logistic regression; sigmoid function; Feedforward; Backpropagation; regularization parameter;
Abstract
One of the challenge we face in human vision is recognizing handwritten digits, since digits writing by free hand may differ from one person to another, sometimes it can be difficult to identify exact type of digits due to their shape and style upon which the digit is written. Automatic recognition of handwritten digits using multi-layer sigmoid neural network provides a solution to this problem. This approach employs the use of sigmoid neuron with feedforward and backpropagation technique. This tool can ensure accuracy of more than 98 percent in recognizing various handwritten digits.
Other Latest Articles
- Adaptation of Plantar Skin to Palmar Skin
- Protective Effect of Kombucha on Diabetic Nephropathy in Streptozotocin - Induced Diabetic Rats
- Genetic Algorithm for the Stable Marriage Problem (SMP)
- A Comparison of the Relationship between Malaria Parasite Density and Some Haematological Parameters in Malaria Infected Male and Female Subjects
- Volvulus of the Sigmoid Colon - A Changing Approach in its Management
Last modified: 2021-07-01 14:32:41