LEARNING FRAMEWORK MODELS
Models of Machine Learning
Supervised Machine Learning
The foundation of supervised machine learning is monitoring. In the supervised learning algorithm,
this means that we retrain the computers using the "labelled" sample and then the computer
forecasts the outcome from the training data.. Here, the labelled data indicates which inputs have
already been mapped to which outcome.More precisely, we may state that after training the
computer with input and related outcome, we challenge it to anticipate the result using training
examples.
Supervised Learning
Source: datatron.com
Classification
A classifier tries to infer some meaning from the values that were seen
A categorization model will attempt to forecast the value of one or more outputs given one or
more inputs. Labels that can be used on a dataset are outcomes.
Classification models include logistic regression, decision tree, random forest, gradient-boosted
tree, multilayer perceptron, one-vs-rest and Naive Bayes.
Logistic Regression
The sigmoid function mentioned above is used in logistics regression to return the likelihood of
a label
It is widely used when the classification problem is binary - true or false, win or lose, positive or
negative
The sigmoid function generates a probability output
© 2024 Athena Global Education. All Rights Reserved
, Source: visual-design.net
Decision Tree
Every branch of a decision tree that is built using a hierarchy technique can be viewed as an if-
else expression
By dividing the database into types depending on the most crucial properties, the branches are
formed
The decision tree's branches are where the final classification takes place
Source: visual-design.net
Random Forest
A cluster of decision trees is called Random Forest
It is a typical form of ensemble method that combines the findings from various predictors
Furthermore, random forest makes use of the bagging technique, which enables each tree to be
trained on a random sample of the original dataset and obtains the consensus of the trees.
Because there are additional layers added to the model, it provides stronger generalization than
decision trees but is less subject to interpretation.
© 2024 Athena Global Education. All Rights Reserved
Models of Machine Learning
Supervised Machine Learning
The foundation of supervised machine learning is monitoring. In the supervised learning algorithm,
this means that we retrain the computers using the "labelled" sample and then the computer
forecasts the outcome from the training data.. Here, the labelled data indicates which inputs have
already been mapped to which outcome.More precisely, we may state that after training the
computer with input and related outcome, we challenge it to anticipate the result using training
examples.
Supervised Learning
Source: datatron.com
Classification
A classifier tries to infer some meaning from the values that were seen
A categorization model will attempt to forecast the value of one or more outputs given one or
more inputs. Labels that can be used on a dataset are outcomes.
Classification models include logistic regression, decision tree, random forest, gradient-boosted
tree, multilayer perceptron, one-vs-rest and Naive Bayes.
Logistic Regression
The sigmoid function mentioned above is used in logistics regression to return the likelihood of
a label
It is widely used when the classification problem is binary - true or false, win or lose, positive or
negative
The sigmoid function generates a probability output
© 2024 Athena Global Education. All Rights Reserved
, Source: visual-design.net
Decision Tree
Every branch of a decision tree that is built using a hierarchy technique can be viewed as an if-
else expression
By dividing the database into types depending on the most crucial properties, the branches are
formed
The decision tree's branches are where the final classification takes place
Source: visual-design.net
Random Forest
A cluster of decision trees is called Random Forest
It is a typical form of ensemble method that combines the findings from various predictors
Furthermore, random forest makes use of the bagging technique, which enables each tree to be
trained on a random sample of the original dataset and obtains the consensus of the trees.
Because there are additional layers added to the model, it provides stronger generalization than
decision trees but is less subject to interpretation.
© 2024 Athena Global Education. All Rights Reserved
