6. Network architecture
Feed forward network is adopted here as this architecture is reported to be suitable for problem based on problem identification. Pattern matching is basically an input/output mapping problem. Closer the mapping, better performance of the network.
The architecture of the network is tabulated below:
1 No. of input neurons: 2
2. No. of output neurons: 1
3. No. of hidden layers: 1
4. No. of hidden neurons: 5
5. No. of training epochs: 458
6. No. of training datasets: 150
7. No. of testing datasets: 20
8. Error goal: 0.0