Skip to main content
. 2020 Nov 4;20(21):6281. doi: 10.3390/s20216281

Table 4.

Characteristics and principal results of the Multi-Layer Feed forward artificial neural Network (MLFN) model (training and internal test) in predicting the coral activity status (i.e., bloated vs. non-bloated) for the training and the test sets.

Training (70%)
Number of cases 1150
Number of hidden layers 1
Number of nodes 9
Training time 0:7:02
Number of trials 500
% bad predictions 0.26 (3)
Testing (30%)
Number of cases 503
% bad predictions (N) 31 (156)