Function Approximations using FF Networks

Suresh Kumar Pandian


The inherent capability of neural networks to perform massive parallel processing of information enhance the approximation of fuzzy systems by neural networks. Chen, Cybenko, Funahashi, Babri and others studied function approximation capabilities by feedforward neural networks. Ramakrishnan and others used sigmoidal signals to study the approximations of continuous functions. In this effort, the right sigmoidal signal is used to establish function approximation theorems.


Neuro-fuzzy systems, feedforward networks, activation function, Sigmoidal, function approximation, fuzzification, etc.,

Full Text:



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ACMA©: World Science Publisher United States