The error reduction ratio is used to define the sensibility of input data to output, and the sensibility is used as
growth criteria. An efficient incremental sequential learning algorithm for fuzzy neural networks(ISL-FNN) is presented,
where the structure learning algorithm incorporating a pruning strategy into new growth criteria is developed. The
performance of ISL-FNN is compared with several existing algorithms on some benchmark problems. Simulation results
show that ISL-FNN has morosimple structure and better accuracy with less number of rules compared to other algorithms.