This is an old version of the compendium, written May 31, 2016, 12:37 p.m. Changes made in this revision were made by iverjo. View rendered version.

TDT4173: Machine Learning and Case-Based Reasoning

# Introduction ## Well Posed Learning Problems __Definition__: A computer program is said to __learn__ from experience _E_ with respect to some class of tasks _T_ and performance measure _P_ if its performance at tasks in _T_, as measured by _P_, improves with experience _E_. An example of a task, inspired by [MarI/O](https://www.youtube.com/watch?v=qv6UVOQ0F44): - Task _T_: Playing the first level of Super Mario Bros. - Performance measure _P_: How far the Mario character is able to advance. - Training experience _E_: Playing the level over and over. ## Inductive bias

Inductive bias is the set of assumptions needed to be able to process input data that the system has not encountered before, and predict the output (correctly). If the system cannot do that at all, then it has also not learned anything other than the specific examples that it has been trained on. In that case, it is basically just a key-value store. That is why inductive bias is so important in machine learning. ## Candidate elimination algorithm ## Decision tree learning with ID3 ## Overfitting ## Cross validation