Using H2O DeepLearning and a Tanh activation function, is it acceptable/valid to get a predicted (probability) value greater than 1? Details: I am using H2O for Deep Learning Artificial Neural Networks in R to predict 2 classes. My y data (actualResults) are the actual classifications of only 0s and 1s. The x independent variables are all numerical and the training frame excludes the y (actualResults). When I do a max on the predicted values, I get values greater than 1, never less than -1, though Tanh is suppose to be limited to [-1, 1]. Note: In the code below, the training_set and testing_set's first column is the actual classification, so -c(1) removes it for the network's input.