Optimal Feed Forward MLPArchitecture for Off-Line Cursive Numeral Recognition
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 1
Abstract
The purpose of this work is to analyze the performance of back-propagation feed-forward algorithm using various different activation functions for the neurons of hidden and output layer and varying the number of neurons in the hidden layer. For sample creation, 250 numerals were gathered form 35 people of different ages including male and female. After binarization, these numerals were clubbed together to form training patterns for the neural network. Network was trained to learn its behavior by adjusting the connection strengths at every iteration. The conjugate gradient descent of each presented training pattern was calculated to identify the minima on the error surface for each training pattern. Experiments were performed by selecting different combinations of two activation functions out of the three activation functions logsig, tansig and purelin for the neurons of the hidden and output layers and the results revealed that as the number of neurons in the hidden layer is increased, the network gets trained in small number of epochs and the percentage recognition accuracy of the neural network was observed to increase up to certain level and then it starts decreasing when number of hidden neurons exceeds a certain level.
Authors and Affiliations
Amit Choudhary , Rahul Rishi , Savita Ahlawat , Vijaypal Singh Dhaka
Keywords
Related Articles
- EP ID EP144923
- DOI -
- Views 75
- Downloads 0
A Survey on Hadoop Assisted K-Means Clustering of Hefty Volume Images
The objects or the overview of the objects in a remote sensing image can be detected or generated directly through the use of basic K-means clustering method. ENVI, ERDAS IMAGINE are some of the software that can be used...
Iris recognition based on subspace analysis
Biometrics deals with the uniqueness of an individual arising from their physiological or behavioral characteristics for the purpose of personal identification. Among many biometrics techniques, iris recognition is one o...
The State of Information and Communication Technology in Iran
Abstract—The development of information and communication technologies depend on several factors like government policy that encourage investors to spend their money in building IT infrastructure and force business or pa...
Dynamic Resource Allocation in Desktop Grids
Grid computing (or the use of computational grids) is the application of several computers to a single problem at the same time. In grid computing ,the computing becomes pervasive and individual users(or client applicati...
Performance Of OLSR Routing Protocol Under Different Route Refresh Intervals In Ad Hoc Networks
An ad hoc wireless network consists of mobile terminals communicating with each other without the help of traditional infrastructure for communication. Optimized Link State Protocol (OLSR) is a proactive routing protoco...