Neural networks rationale

Figure 10.5(b) Prediction with no variable selection. The experimental rationale was as for part (a), except that the artificial neural network was run on all 150 variables, that is, no variable selection was used. Optimization in this case resulted in having 8 nodes in the hidden layer the outputs were obtained after 10 000 epochs with an error on the calibration set of 0.01 6 out of 15 (40%) unadulterated samples and 12 out of 15 (80%) adulterated samples were predicted correctly. It may be seen that very poor separation was achieved - the two data bases do not line up on the predictive value of 0 or 1 but form a loose cloud in the middle area around 0.5, indicating that the net was unable to separate the two groups clearly. 

---