Please enable JavaScript.
Coggle requires JavaScript to display documents.
Supervised Learning (Distribution (Unknown, Assume identical,…
Supervised Learning
Distribution
-
Assume identical, independently distributed
Training Issues
-
Overfitting
hypothesis captures too much noise from the data, unable to generalize
-
-
-
-
-
-
Goal: find a hypothesis which as has “low” expected error, using the training set.
-