Skip to main content
. 2020 Jan 7;3:3. doi: 10.1038/s42003-019-0729-3

Table 2.

The confusion matrix table for the example in Fig. 5a.

Deep-Channel predicted labels
0 1 2 3 4 5
True labels 0 96890 726 0 0 0 0
1 9 2371 0 0 0 0
2 0 0 0 0 0 0
3 0 0 0 0 0 0
4 0 0 0 0 0 0
5 0 0 0 0 0 0

Label 0 = no channels open, label 1 = one channel open. Note that Deep-Channel is trained to recognise up to 5 channels opening at a time, however, with only one channel active at a time, the maximum ground truth class (True Label) is label 1 (one channel open). The emboldened numbers are the number of data points correctly predicted by Deep-Channel