Machine learning/Supervised Learning

From Wikiversity
Jump to navigation Jump to search

Supervised learning is a type of machine learning algorithm that uses a known dataset (called the training dataset) to make predictions.

Supervised learning includes two categories of algorithms:

  • Classification: for categorical response values, where the data can be separated into specific “classes”
  • Regression: for continuous-response values

Classification[edit | edit source]

  • Support vector machines (SVM)
  • Neural networks
  • Linear classifiers: a group of algorithms such as:
    • Logistic regression
    • Perceptron
    • Fisher's linear discrimination
    • Naïve Bayes classifier
  • Decision trees: a group of algorithms such as
    • Random forest
    • Bootstrap aggregation
    • Boosting
  • Discriminant analysis
  • Nearest neighbors (kNN): A Non-parametric and instance-based method used for classification and regression

Regression[edit | edit source]

  • Linear regression
  • Nonlinear regression
  • Generalized linear models
  • Decision trees: a group of algorithms such as
    • Random forest
    • Bootstrap aggregation
    • Boosting
  • Neural networks