Active Learning

Active learning is a special case of machine learning in which a learning algorithm can interactively query a user to label new data points with the desired outputs.

How Active Learning Works

Initialization:

1. Start with a small labeled dataset and train an initial model.
2. Have a much larger pool of unlabeled data.

Uncertainty Sampling:

1. The model makes predictions on the unlabeled data.
2. It then identifies instances where it's most uncertain (e.g., those for which the predicted class probabilities are closest to 50% in a binary classification task).

Query for Labels:

1. The model (or system) queries the user or expert to label the instances it's uncertain about.

Update the Model:

1. Incorporate the newly labeled instances into the training dataset.
2. Retrain the model using the updated dataset.

Iterate:

1. The process is repeated, with the model iteratively selecting uncertain data points, querying for their labels, and updating its knowledge.