With a parametric algorithm, the model is specified by the user and the algorithm determines parameters to plug into that model. A classic example is linear regression: the predictor variables and the way they interact is specified by the user, and the algorithm learns the optimal coefficients during the training phase.
Parametric algorithms are appropriate whenever the supplied information about the model is certain or probable in advance. They generally yield better results than nonparametric algorithms provided the assumptions made are correct.
- used by
- ALG_Actor-critic ALG_Averaged one-dependence estimators ALG_Bayesian linear regression ALG_Bayesian network ALG_Discriminant analysis ALG_Least Squares Regression ALG_Logistic regression ALG_Markov random field ALG_Monte-Carlo tree search ALG_Multivariate adaptive regression splines ALG_Naive Bayesian Classifier ALG_One Rule ALG_Q-learning ALG_SARSA ALG_Stepwise Regression ALG_Support vector machine ALG_Temporal difference learning