Next: Dealing with Error
Up: Evaluating Hypothesis and Experimental
Previous: Problems with Estimating Accuracy
- Random variation in the selection of the test data.
- Random variation in the selection of the training data.
- Randomness in the learning algorithm (e.g., initial weights).
- Random classification error.
Patricia Jean Riddle
Wed Jun 23 13:06:34 NZST 1999