Model-based Learning Algorithm

A Model-based Learning Algorithm is a learning algorithm that can be applied by a model-based learning system to solve a model-based learning task (which requires the production of a model-based prediction function).

• AKA: Supervised Model-based Learning Algorithm, Model-based Training Algorithm.
• Context:
  • It can range from being a Supervised Model-based Learning Algorithm to being an Unsupervised Model-based Learning Algorithm.
  • It can range from being a Model-based Classification Algorithm to being a Model-based Ranking Algorithm to being a Model-based Estimation Algorithm.
  • It can range from being a Lazy Model-based Learning Algorithm to being an Eager Model-based Learning Algorithm.
  • It can range from being a Discriminative Learning Algorithm to being a Generative Learning Algorithm.
• Example(s):
  • a Regression Algorithm, such as a least-squares function fitting algorithm.
  • a Statistical Modeling Algorithm, such as s Linear Model Learning Algorithm or a Logistic Regression Model Learning Algorithm.
  • a Decision Tree Learning Algorithm, such as a C4.5 Algorithm.
  • a Discriminative Machine Learning Algorithm, such as a logistic regression.
  • a Neural-Network Learning Algorithm, such as a backprop learning algorithm.
  • a Kernel-based Learning Algorithm, such as an SVM algorithm.
  • …
• Counter-Example(s):
  • an Instance-based Learning Algorithm, such as: k-Nearest Neighbor Algorithm.
  • a Locally Weighted Regression Algorithm.
• See: Unsupervised Learning Algorithm.

---

---

References

1993

• (Quinlan, 1993) ⇒ J. Ross Quinlan. (1993). “Combining Instance-based and Model-based Learning.” In: Proceedings of the Tenth International Conference on Machine Learning.

---