Identification of a Typical CSTR Using Optimal Focused Time Lagged Recurrent Neural Network Model with Gamma Memory Filter

Table 2

Parameters of Fully Recurrent NN (Lab. data). Number of Exemplars: Training = 306, Testing = 77, Max epoh = 1000, memory-axon, Norm → L1.

Sr. no.	Parameters	Hidden layer # 1	Output layer
1	Processing Elements	18	1
2	Transfer function	tan h	tan h
3	Learning rule	Momentum	Momentum
4	Step size	0.1	0.1
5	Momentum	0.7	0.7