Rate the Article: Automatic Recognition of Handwritten Digits Using Multi-Layer Sigmoid Neural Network, IJSR, Call for Papers, Online Journal
International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064

Downloads: 119 | Views: 401

Research Paper | Electronics & Communication Engineering | China | Volume 5 Issue 3, March 2016 | Rating: 6.1 / 10


Automatic Recognition of Handwritten Digits Using Multi-Layer Sigmoid Neural Network

Said Kassim Katungunya, Xuewen Ding, Juma Joram Mashenene


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.


Keywords: logistic regression, sigmoid function, Feedforward, Backpropagation, regularization parameter


Edition: Volume 5 Issue 3, March 2016,


Pages: 951 - 955



Rate this Article


Select Rating (Lowest: 1, Highest: 10)

5

Your Comments (Only high quality comments will be accepted.)

Characters: 0

Your Full Name:


Your Valid Email Address:


Verification Code will appear in 2 Seconds ... Wait

Top