Update examples on algorithms section (#38)

Author: mirand863

docs/source/algorithms/local_classifier_per_level.rst

@@ -8,8 +8,6 @@ The local classifier per level approach consists of training a multi-class class
 .. figure:: local_classifier_per_level.svg
    :align: center
 
-   Visual representation of the local classifier per level approach, adapted from [1]_.
+   Visual representation of the local classifier per level approach.
 
-Similar to the other hierarchical classifiers, the local classifier per level can also be trained in parallel and prediction is performed in a top-down style to avoid inconsistencies. For example, supposing that for a given test example the classifier at the first level returns the probabilities 0.91 and 0.7 for classes 1 and 2, respectively, then the one with the highest probability is considered as the correct prediction, which in this case is class 1. For the second level, only the probabilities for classes 1.1 and 1.2 are considered and the one with the highest probability is the final prediction.
-
-.. [1] Silla, C. N., & Freitas, A. A. (2011). A survey of hierarchical classification across different application domains. Data Mining and Knowledge Discovery, 22(1), 31-72.
+Similar to the other hierarchical classifiers, the local classifier per level can also be trained in parallel, and prediction is performed in a top-down style to avoid inconsistencies. For example, supposing that for a given test example the classifier at the first level returns the probabilities 0.91 and 0.7 for classes "Reptile" and "Mammal", respectively, then the one with the highest probability is considered as the correct prediction, which in this case is class "Reptile". For the second level, only the probabilities for classes "Snake" and "Lizard" are considered and the one with the highest probability is the final prediction.

docs/source/algorithms/local_classifier_per_level.svg

@@ -8,14 +8,12 @@ One of the most popular approaches in the literature, the local classifier per n
 .. figure:: local_classifier_per_node.svg
    :align: center
 
-   Visual representation of the local classifier per node approach, adapted from [1]_.
+   Visual representation of the local classifier per node approach.
 
 .. toctree::
     :hidden:
 
     training_policies
     selecting_training_policy
 
-Each binary classifier is trained in parallel using the library `Ray <https://www.ray.io/>`_. In order to avoid inconsistencies, prediction is performed in a top-down manner. For example, given a hypothetical test example, the local classifier per node firstly queries the binary classifiers at nodes 1 and 2. Let's suppose that in this case the probability of the test example belonging to class 1 is 0.8, while the probability of belonging to class 2 is 0.5, then class 1 is picked. At the next level, only the classifiers at nodes 1.1 and 1.2 are queried, and again the one with the highest probability is selected.
-
-.. [1] Silla, C. N., & Freitas, A. A. (2011). A survey of hierarchical classification across different application domains. Data Mining and Knowledge Discovery, 22(1), 31-72.
+Each binary classifier is trained in parallel using the library `Ray <https://www.ray.io/>`_. In order to avoid inconsistencies, prediction is performed in a top-down manner. For example, given a hypothetical test example, the local classifier per node firstly queries the binary classifiers at nodes "Reptile" and "Mammal". Let's suppose that in this case the probability of the test example belonging to class "Reptile" is 0.8, while the probability of belonging to class "Mammal" is 0.5, then class "Reptile" is picked. At the next level, only the classifiers at nodes "Snake" and "Lizard" are queried, and again the one with the highest probability is selected.