Machine Learning focuses on complex representations and search methods for specialized data-intensive problems. Different machine learning methods utilize the specific prior knowledge associated with the collected data. Such methods are generally more dependent on the domain of the data.
A key issue with machine learning is generalization of the techniques. Generalization deals with the robustness of the techniques when dealing with variation of data from the same domain.
Empirical Validation is used to authenticate the results obtained from the different machine learning techniques. Key issues here are statistical soundness and computational efficiency of the methods used for validation. Exhaustive validation techniques are also used for small sized datasets, but validation is usually constrained by finite computing and data resources.
Challenges from KDD:
|
|
Scalability. |
|
|
Cost Information. |
|
|
Automatic Data-Preprocessing. |
![]()