In supervised learning, which of the following is trained using labeled input data?

The correct answer is that predictors and targets are trained using labeled input data in supervised learning. This learning paradigm involves two main components: the predictor, which is the input data that contains the features or independent variables, and the target, which represents the output or dependent variable that the model aims to predict.

In supervised learning, the model learns to map these inputs to the corresponding outputs based on the labeled dataset where each input is associated with a specific known output. This process enables the model to make predictions on new, unseen data by applying what it has learned from the training data.

The other options do not accurately define the concept of supervised learning. Unlabeled data does not provide the necessary information for training a model to predict outputs since it lacks associated targets. Autonomous outputs suggest a model that operates without external input or guidance, which is not reflective of the supervised learning approach. Lastly, while statistical models are used in supervised learning, they are a broader category and do not define the relationship between labeled input data and targets specifically.