Skip to Main Content
Humans are not perfect and they make mistakes. For example, humans without computer aided tools would not be able to design VLSI chips larger than 100 transistors. Computers are assisting humans in many aspects of their life. For many years already computers were used for number crunching, office related jobs, etc. More recently computers are used for making intelligent decisions. The methods of computational intelligence are relatively successful, but these methods have to be used with great care. In this presentation advantages and disadvantages of fuzzy and neural networks are presented. It turns out that often popular training algorithms are not capable of tuning neural networks to proper accuracy without losing generalization abilities. Also, abilities of neural networks strongly depend on the used architecture, and surprisingly the most popular architectures usually are least powerful.