Neural Network for Pattern Classification
Journal Title: International Journal of engineering Research and Applications - Year 2017, Vol 7, Issue 12
Abstract
Neural Networks (NN) are the most active research and application in the field of pattern classification, using training and testing data to build a model. However, the success of the networks is highly dependent on the performance of the training process and hence the training algorithm. Many training algorithms have been proposed so far to improve the performance of neural networks. The paper gives the study of multilayer perceptron, radial basis function network, and probabilistic neural network. The algorithms are tested on three different datasets and comparisons in terms of accuracy with test data are mentioned in the paper.
Authors and Affiliations
Rashmi Amardeep, Dr. K Thippe Swamy
Keywords
Related Articles
- EP ID EP393246
- DOI 10.9790/9622-0712064044.
- Views 118
- Downloads 0
Technology and Key Strategy of IE4 Permanent Magnet Brushless DC Motor Drive for Electric Vehicle Application
Environmental protection and energy conservations are the main concern of 21st century Asia Pacific developing countries. This concern has compelled to design and develop zero pollution road transportation Electric Vehic...
On the Architecture and Design of Multi-Wavelength Passive Optical Arrayed Waveguide Grating Routers
Fiber to the premises (FTTP) technology has become an attractive solution in the last two decades to overcome many limitations appeared with the wireless and copper based technologies in access network. Most of FTTP depl...
Registration of the Characteristic Curves of Caned Pump
The paper reports investigation fixed speed caned pump Characteristic which includes flow, pressure, power consumed and pump efficiency under condition of atmospheric pressure and temperature in ShuwaikhKuwait. The exper...
Self-organizing Behavior of Y-junctions of Graphene Nanoribbons
With the help of our molecular dynamics simulation we want to motivate emerging and development of technological methods for building of carbon nanostructure networks. We shall study self-organizing behaviors of graphene...
Effect of Soil Flexibility on Analysis and Design of Building
Generally in the analysis and design of multi-story building frame it is assumed that the base is fixed but in actual the structure is ultimately supported on soil which is flexible in nature. This flexibility of soil ma...