Overview
Supervised and semi-supervised learning are two important paradigms in machine learning. Supervised learning relies on labeled data to train models, allowing them to make predictions based on known outcomes. This approach is widely used in applications like email filtering and image recognition. On ...
Key Terms
Example: Images of cats labeled as 'cat' and dogs labeled as 'dog'.
Example: A collection of images without any labels.
Example: Classifying emails as spam or not spam.
Example: Using a model trained on a small dataset to predict labels for a larger dataset.
Example: Using text and images to train separate models that help each other improve.
Example: Shows true positives, false positives, true negatives, and false negatives.
Related Topics
Unsupervised Learning
A type of machine learning that uses data without labels to find patterns.
intermediateDeep Learning
A subset of machine learning that uses neural networks with many layers.
advancedReinforcement Learning
A type of machine learning where an agent learns to make decisions by receiving rewards or penalties.
advancedKey Concepts
Labeled DataUnlabeled DataModel TrainingClassification