Refactor LR focal loss doc

Co-authored-by: Jacob Sznajdman <[email protected]>

Author: brs96

doc/modules/ROOT/images/equations/focal-loss.svg

@@ -31,10 +31,11 @@ When `focusWeight` is a value greater than zero, the loss function changes from
 
 image::equations/focal-loss.svg[align="center"]
 
-The `focusWeight` parameter is the exponent noted as Greek letter gamma.
-Increasing `focusWeight` will guide the model towards trying to fit "hard" examples.
-A "hard" example is an example for which the model has a low predicted probability for the true class.
-In the above equation, the loss will be exponentially higher for low-probability examples, thus tuning the model towards trying to fit them, at the expense of potentially losing some "easy" examples.
+where `p~t~` denotes the probability of the true class.The `focusWeight` parameter is the exponent noted as Greek letter gamma.
+
+Increasing `focusWeight` will guide the model towards trying to fit "hard" misclassified examples.
+A hard misclassified example is an example for which the model has a low predicted probability for the true class.
+In the above equation, the loss will be exponentially higher for low-true-class-probability examples, thus tuning the model towards trying to fit them, at the expense of potentially being less confident on "easy" examples.
 
 In class-imbalanced datasets, the minority class(es) are typically harder to classify correctly.
 Read more about class imbalance for Link Prediction in xref:machine-learning/linkprediction-pipelines/theory.adoc#linkprediction-pipelines-classimbalance[Class Imbalance].

doc/modules/ROOT/pages/machine-learning/training-methods/logistic-regression.adoc

@@ -7,5 +7,5 @@ include::partial$/machine-learning/training-methods/gradient-descent-common-conf
 
 include::partial$/machine-learning/training-methods/penalty-common-config.adoc[]
 
-| focusWeight | Float | 0.0     | yes      | Exponent for the focal loss factor, to make the model focus more on hard, misclassified examples in the train set. By default, no focus is applied. Must be positive.
+| focusWeight | Float | 0.0     | yes      | Exponent for the focal loss factor, to make the model focus more on hard, misclassified examples in the train set. The default of `0.0` implies that focus is not applied and cross entropy is used. Must be positive.
 |===