Thumbnail
Access Restriction
Open

Author Thammano, Arit ♦ Klomiam, Narodom
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword New Neural Network Classifier ♦ Cross-correlation Neural Network ♦ Classification Problem ♦ Experimental Result ♦ Incoming Input Pattern ♦ Excellent Classifier ♦ Many Different Structure ♦ Benchmark Problem ♦ Fuzzy Artmap Neural Network ♦ Previous Research ♦ New Neural Network Approach ♦ Reference Pattern ♦ Neural Network ♦ Training Sample
Abstract Abstract:- A neural network is an excellent classifier; however, its performance depends directly on the size and quality of training samples presented to the network. This paper proposes a new neural network approach to deal with the classification problem by applying the concept of cross-correlation to measure the likeness or similarity between the incoming input pattern and the reference patterns of each class. This proposed model has been benchmarked against the fuzzy ARTMAP neural network and many other different structures studied in the previous researches. The experimental results on four benchmark problems show that the proposed network has the best performance among all.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article