• Kirti Vidyadhar Khedkar
• Manisha Sachin Mahindrakar

The Fuzzy Hypersphere Neural Network classifier uses fuzzy hyperspheres as cluster and classes which are represented as a union of FHS and in Class-specific fuzzy hypersphere neural network clustering is elaborated on inter-class and intra-class fuzzy membership to create fuzzy hyperspheres in the hidden layer. Class-specific FHSNN has two algorithms Rule 1 and Rule 2 for the inclusion of pattern in hypersphere, visualization and to eliminate the overlap between hyperspheres. The performance of class-specific fuzzy hypersphere neural network is analyzed with a fuzzy hypersphere neural network and it found that Class-specific FHSNN is superior with the accuracy of a dataset having a large number of patterns.

Fuzzy Hypersphere Neural Network (FHSNN), Class-specific fuzzy hypersphere neural network (CSFHSNN), fuzzy hypersphere, Supervised and unsupervised learning

"Analysis of Classification Algorithms Using Neuro-Fuzzy Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.39-41, June 2019, Available :http://www.jetir.org/papers/JETIR1906G73.pdf

"Analysis of Classification Algorithms Using Neuro-Fuzzy Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp39-41, June 2019, Available at : http://www.jetir.org/papers/JETIR1906G73.pdf