Fuzzy Min Max Neural Network for pattern classification: An overview of complexity problem

• Main Authors: Al Sayaydeh, Osama Nayel, Shamaileh, Abeer
• Format: Article
• Language: English
• Published: IJITLS, UAE 2018
• Subjects: QA Mathematics
• Online Access: http://umpir.ump.edu.my/id/eprint/23976/1/Fuzzy%20Min%20Max%20Neural%20Network%20for%20pattern.pdf; http://umpir.ump.edu.my/id/eprint/23976/; http://journals.sfu.ca/ijitls/index.php/ijitls/article/view/54
• Institution: Universiti Malaysia Pahang

Over the last years, the pattern classification is considered one of the most significant domains in artificial intelligence (AI), because it shapes a fundamental in many diverse real live applications where the artificial neural networks (ANNs) and fuzzy logic (FL) are most extensively utilized in pattern classification. In order to construct an effective and robust classifier, researchers have invented hybrid systems that combine both FL and ANNs. The Fuzzy Min Max (FMM) neural network has been proven to be a robust classifier for handling pattern classification issues. Although FMM has several features, it suffers from several limitations. Thus, researchers have introduced a lot of improvements to beat the shortcomings of FMM neural network. This paper focuses on a complete review of developments carried out on FMM neural network for addressing the complexity problem in order to help new researchers in identifying the recent strategies used to address the complexity problem.