The multilayer perceptron is an artificial neural network that learns nonlinear function mappings. Nonlinear functions can be represented by multilayer perceptrons with units that use nonlinear activation functions. The neurons in the multilayer perceptron networks typically employ sigmoidal activation function. The next state of the J-K fuzzy flipflops (F3) using Fodor, Yager and Dombi operators present S-shaped characteristics. An interesting aspect of F3-s might be that they have a certain convergent behavior when one of their inputs (e.g. J) is exited repeatedly. If J is considered the equivalent of the traditional input of a neuron (with an adder unit applied before J), K might play a secondary modifier's role, or can just be set fix. The paper proposes the investigation of such possible F3-networks as new alternative types of neural networks.