Title: Analysis on Pattern Classification using Artificial Neural Networks
Abstract:Artificial neural networks (ANN) is one of the most dynamic research and application areas for pattern classification. ANN is the branch of Artificial Intelligence (AI). The network is trained by 'n' ...Artificial neural networks (ANN) is one of the most dynamic research and application areas for pattern classification. ANN is the branch of Artificial Intelligence (AI). The network is trained by 'n' number of algorithm like back propagation algorithm. The different combinations of performance functions are used for training the ANN. The back propagation neural network (BPNN) can be used as a highly successful algorithm for pattern classification with suitable combination of performance functions while training and learning ANN. When the maximum likelihood algorithm was compared with back propagation neural network method, the BPNN was more accurate than other algorithms. A Multilayer feed-forward neural network algorithm is also used for pattern classification. However BPNN gives more effective results than other pattern classification algorithms. Handwriting Recognition (or HWR) is the ability of a machine to receive and interpret handwritten input from different sources like paper documents, photographs, touch-screens and other input devices. Various performance functions is examined in this paper so as to get to a conclusion that which function would be better for usage in the network to produce an efficient and effective system. The training of back propagation neural network is done with the application of Offline Handwritten Character Recognition.Read More
Publication Year: 2016
Publication Date: 2016-04-02
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot