Active Learning
**Problem:** Implement an active learning strategy to select the most informative samples from a dataset for labeling.
**Example:** Suppose we have a dataset of images and their corresponding labels. We want to select the most informative samples from the dataset for labeling. One active learning strategy is to use the uncertainty of the model as a criterion for selecting the samples. We can use the entropy of the model's output as a measure of uncertainty.
**Constraints:** The active learning strategy should be implemented to select the most informative samples from the dataset.
Test Cases
Test Case 1
Input:
[[1, 2], [3, 4]]Expected:
[1, 0]Test Case 2
Input:
[[5, 6], [7, 8]]Expected:
[0, 1]+ 3 hidden test cases