RNN = Recurrent Neural Network

two passes


Precision=TP/(TP+FP) - false positive -> 0
Recall=TP/(TP+FN) - tp -> 0
F1=2Precision⋅Recall​/(Precision + Recall)
Accuracy = (TP+TN)/(TP+TN+FP+FN)


false positive false negative

true pred


FP A = pred = A  true != A
FN A = true = A  pred != A