Across
- 4. measuring of suitability of alternative independent variables
- 6. Useful in comparing regression models capability to predict
- 7. In this case the training data does not include any desired output
- 9. A method that use the inbuilt structures in the data for a better organization of the data
- 12. fitting one example to a known class
- 15. Selecting right model
- 17. Computing linear correlation after ranking the variable values
- 18. Transforms all the values of any attribute to zero mean and standard deviation one
- 19. measures the uncertainty associated with a probability distribution
- 20. this problem can be solved by using constraints on model parameters
Down
- 1. the developed model is such that the user can only test the model but cannot know how it is working
- 2. learns through the induction process
- 3. Normally used any time you use a common noun
- 5. the process in which the subnodes of a decision node are removed
- 8. Correcting/removing inconsistencies, inaccuracy, irregularities etc in the data
- 9. Using many models to generate the estimate of the required variable
- 10. used to control the learning process
- 11. Proving requires conducting experiments
- 13. error related to misestimating the mean
- 14. the process that is used to classify nodes into two or more sub-nodes
- 16. A method that has no assumptions regarding the structures or spatial distribution