Answers

1. In supervised learning, we provide the desired output with the training data. The desired output is not included as part of the training data for unsupervised learning.
2. Cross-validation is a statistical technique that's used to measure the performance of an ML model. In k-fold cross-validation, we divide the data into k folds or slices. We train our model using the k-1 slices of the dataset and test the accuracy of the model using the kth slice. We repeat this process until each kth slice is used as testing data. The cross-validation accuracy of the model is computed by taking the average of the accuracy of all the models we built through k iterations.
3. RandomizedSearchCV is a tool that's available with scikit-learn for applying cross-validation functionality to an ML model for randomly selected hyperparameters. GridSearchCV provides similar functionality to RandomizedSearchCV, except that it validates the model for all the combinations of hyperparameter...