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 90
- Downloads 0
Two-Level Dynamic Load Balancing Algorithm Using Load Thresholds and Pairwise Immigration
This paper proposes a two-level dynamic load balancing scheme for grid and distributed systems. We focus on reducing average task response time. In order to achieve the goals, efficient dynamic load balancing is required...
Minimizing weighted mean flow time in open shop scheduling with time-dependent weights and intermediate storage cost
Open shop scheduling problem is a common scheduling problem and has wide engineering applications in manufacturing. In some industrial cases, open shop scheduling could be a long scheduling problem as an aircraft product...
Devnagari Handwritten Numeral Recognition using Geometric Features and Statistical combination Classifier
This paper presents a Devnagari Numerical recognition method based on statistical discriminant functions. 17 geometric features based on pixel connectivity, lines, line directions, holes, image area, perimeter, eccentric...
I n d o or Environment Mobile Robot Localization
Robot Localization is an emerging area in recent research and applications. The determination of location or localization is he basic requirement for robots to move in their office nvironment. This proposed work aims t...
IMPROVED SOFTWARE QUALITY ASSURANCE TECHNIQUES USING SAFE GROWTH MODEL
In our lives are governed by large, complex systems with ncreasingly complex software, and the safety, security, and reliability of these systems has become a major concern. As the software in today’s systems grows larg...