Dynamic fuzzy learning rate in a self-evolving interval type-2 TSK fuzzy neural network

Position tracking of a 3-PSP parallel robot using dynamic growing interval type-2 fuzzy neural control

“…As increases, oscillation in the proximity of the solution increases. On the other hand, small values of learning rate lead to slower convergence speed of the gradient descent algorithm [35]. The convergence of the system can be guaranteed by defining a proper value for .…”