Applied Computational Intelligence and Soft Computing / 2009 / Article / Tab 2

Research Article

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.ParametersHidden layer # 1Output layer

1Processing Elements181
2Transfer functiontan htan h
3Learning ruleMomentumMomentum
4Step size0.10.1
5Momentum0.70.7

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.