Difference between revisions of "Cross-Validation"
| Line 12: | Line 12: | ||
* [[Feature Exploration/Learning]] | * [[Feature Exploration/Learning]] | ||
* [[Recursive Feature Elimination (RFE)]] | * [[Recursive Feature Elimination (RFE)]] | ||
| − | |||
| − | |||
| − | a technique for evaluating ML models by training several ML models on subsets of the available input data and evaluating them on the complementary subset of the data. Use cross-validation to detect overfitting, ie, failing to generalize a pattern [http://docs.aws.amazon.com/machine-learning/latest/dg/cross-validation.html Developer Guide - Amazon AWS ML] | + | a technique for evaluating Machine Learning (ML) models by training several ML models on subsets of the available input data and evaluating them on the complementary subset of the data. Use cross-validation to detect overfitting, ie, failing to generalize a pattern [http://docs.aws.amazon.com/machine-learning/latest/dg/cross-validation.html Developer Guide - Amazon AWS ML] |
* Method of estimating expected prediction error | * Method of estimating expected prediction error | ||
Revision as of 09:42, 30 May 2020
YouTube search... ...Google search
- Automated Machine Learning (AML) - AutoML
- Principal Component Analysis (PCA)
- Feature Exploration/Learning
- Recursive Feature Elimination (RFE)
a technique for evaluating Machine Learning (ML) models by training several ML models on subsets of the available input data and evaluating them on the complementary subset of the data. Use cross-validation to detect overfitting, ie, failing to generalize a pattern Developer Guide - Amazon AWS ML
- Method of estimating expected prediction error
- Helps selecting the best fit model
- Help ensuring model is not over fit
Types of Cross Validation:
- K-Fold
- Leave One Out
- Bootstrap
- Hold Out
