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 122
- Downloads 0
Analysis On High Rate GNSS Data Co-Seismic Response In Jiuzhaigou 7.0Ms Earthquake
Jiuzhaigou 7.0Ms Earthquake Occured At 13:19 8th August 2017 (UTC) In Sichuan Province, China. We Processed The High Rate (1Hz) Global Navigation Satellite System(GNSS) Data Of Stations In TwoHundred Kilometers Distance...
The Journey of being an Entrepreneur
Entrepreneurs are innovators, willing to take risks and generate new ideas to create unique and potentially profitable solutions to modern-day problems. Entrepreneurship is not so much a skill as a habitual state of mind...
An Investigation of Strength Properties of Concrete Core Samples Obtained in Different Heights and Lines
Concrete is a composite building material wich has a high usage area. The quality and properties of the concrete material produced may vary according to the type of application and the application area. Especially it is...
Morphological Studies in Novel Liquid Rubber Modified Epoxies
The aim of this article is to present morphological studies on the tensile fractured specimens of novel liquid rubber obtained from the pyrolysis of scrap rubber. Such a study is crucial for gaining useful insight into t...
Exploring the features of Infrared Thermography for Friction stir welding process – a tool of new era
Friction stir welding (FSW) is a well-known process adopted for joining of different metals and alloys. The process invented by TWI, UK in 1991, is widely used in marine and aerospace industries. Major thrust was given o...