This network uses gaussian membership functions with two free parameters:

mean and variance. The total number of these parameters is M*N, where M is

the number of rules, N is the number of inputs. There is a hidden set of

parameters of tsk-functions which perform a linear convolution of fuzzy

inference outputs with a set of coefficiants. Total number of these

parameters is M*(N+1). So the total amount of adjusted parameters is

2*M*N + M.

-This network uses gaussian membership functions with two free parameters: mean and variance The total number of these parameters is M* N, where M is the number of rules, N is the number of inputs There is a hidden set of parameters of tsk..-functions which perform a linear convolution of fuzzy inference outputs with a set of coefficiants. Total number of these parameters is M* (N+1). So the total amount of adjusted parameters is 2* M* N+ M.