Skip to Main Content

As the neuron number of the ELM can range over a wide extent to get a good performance, we only list one set-up which has the smallest average testing error. And each set-up of the ELM algorithm is trained 50 times and the average performances are presented in Table 2.

Table 2

The performance of ELM with tansig or logsig as activation function

Activation functionNeuron number Average training time(s)Average training error (%)Average testing error (%)Smallest testing error (%)
Tansig 120 0.1732 5.53 6.23 5.53 
Logsig 80 0.1011 6.55 6.99 6.44 
Activation functionNeuron number Average training time(s)Average training error (%)Average testing error (%)Smallest testing error (%)
Tansig 120 0.1732 5.53 6.23 5.53 
Logsig 80 0.1011 6.55 6.99 6.44 

Close Modal

or Create an Account

Close Modal
Close Modal