The h20 package has been used to fit a NN to the famous iris data. The figure plots the predicted class probabilities vs the petal length variable (with other variables fixed at their means). Which of the following statements accurately summarises the information in the plot, you can choose more than one option. 1.0 0.8 0.6 Species: Setosa Probability Species: Versicolor . . .. . Species: Virginica 0.4 0.2 0.0 -1.5 -1.0 -0.5 0.0 0.5 1.0 1.5 Petal length A. A flower with an average petal length is almost certainly a Versicolor Iris. O) B. We would get a very similar graph if we reran the algorithm with different starting values. O C. It looks like a logistic activation function was used on the output layer. O D. The model predicts that small values of petal length are associated with Setosa, middle values with Versicolor, and high values with Viriginica. O E. The model predicts that a flower with a petal length about 1 standard deviation above the mean is likely to be either the Setosa or the Versicolor species. _ F. The model predicts that a flower with a petal length of around -1 is likely to be either the Setosa or Versicolor species