Supervised learning deals with data that have no labels, while unsupervised learning has labeled data.

Supervised learning uses labeled data to train models, while unsupervised learning uses unlabeled data to discover patterns.

Supervised learning is only for image recognition, while unsupervised learning is only for text classification.

Supervised learning always creates clusters, while unsupervised learning always creates predictions.

ML models can fix incorrect data automatically.

ML models only need large data volumes, not high-quality data.

If the data is biased or contains errors, the model’s predictions can become unreliable or discriminatory.

Poor data simply makes the model train faster.

A design element of the user interface.

A property or variable used as input to a model (e.g., pixel intensity, age, income).

A hidden output from the model.

The final numerical prediction or label the model outputs.