Exam AI-900 topic 1 question 50 discussion

Answers are : 1 = N (By essence validation set is different from test set. Not difficult : the answer is No). 2 = Y (This is the purpose of validation set : to validate (or not) the model). 3 = N (validation test doesn't test if all the train split of dataset has been used to train the model. That's out of the scope).

Answers looks correct If we assume validation set - means test data set

It's worth noting that the validation set should be different from the training set, so that the model doesn't memorize the validation set. Also, it's recommended to have the same distribution of the data in the validation set as in the test set.

I guess it is NNY. https://docs.microsoft.com/en-us/azure/machine-learning/concept-automated-ml#training-validation-and-test-data mentioned: With automated ML you provide the training data to train ML models, and you can specify what type of model validation to perform. Automated ML performs model validation as part of training. That is, automated ML uses validation data to tune model hyperparameters based on the applied algorithm to find the best combination that best fits the training data. However, the same validation data is used for each iteration of tuning, which introduces model evaluation bias since the model continues to improve and fit to the validation data. To help confirm that such bias isn't applied to the final recommended model, automated ML supports the use of test data to evaluate the final model that automated ML recommends at the end of your experiment. When you provide test data as part of your AutoML experiment configuration, this recommended model is tested by default at the end of your experiment (preview).

For me to remember xD Validation set = predicts model = Yes (only yes)

This question is not really clear to my understanding

Official Microsoft documentation is missing. Where? Link ?

Is Test set and Validation set different in Azure ?