ML PORTAL

User Tools

Site Tools

Trace:
glossary

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
glossary [2022/09/12 13:55] – adminglossary [2022/09/12 16:51] (current) – admin
Line 49: Line 49:
 ==== cross-validation ==== ==== cross-validation ====
  
-A method to estimate how well a model will generalise to new data. In cross-validation, the model is trained on non-overlapping subsets of the data and then validated on a remaining not used subset.+A method to estimate how well a model will generalise to new data. In cross-validation, the model is trained on a subset of the data and then validated on the remaining non-overlapping subsets, e.g. [[:glossary#k-fold_cross-validation|k-fold cross-validation]].
  
 ===== D ===== ===== D =====
Line 87: Line 87:
 ==== feature engineering ==== ==== feature engineering ====
  
-The process of converting data into useful [[:glossary#feature|features]] for training a model. [[:glossary#feature_selection|Feature selection]] is a part of feature engineering.+The process of converting data into useful [[:glossary#feature|features]] for training a model.
  
 ==== feature selection ==== ==== feature selection ====
Line 119: Line 119:
 ===== K ===== ===== K =====
  
-==== k-fold validation ====+==== k-fold cross-validation ==== 
 + 
 +The training set is split into k smaller subsets. The model is trained on one of the k folds as training set and validated on the remaining (k-1) folds. This is done for all k folds. The performance measure calculated by the k-fold cross-validation is the average of the results of all k folds.
  
 ===== L ===== ===== L =====
glossary.txt · Last modified: 2022/09/12 16:51 by admin