Supervised learning

Supervised learning is a type of machine learning where models are trained using labeled datasets, meaning each input has a corresponding correct output. The model learns patterns and relationships between inputs and outputs so it can make accurate inferences on new, unseen data.

There are two main types of supervised learning tasks.

• Classification involves predicting categorical outcomes, such as determining whether an email is spam or not, or whether a customer will purchase a product.
• Regression involves predicting continuous values, like forecasting house prices, sales revenue, or stock market trends.

In pre-training, supervised learning can be used to train a model on a large, general labeled dataset to learn foundational patterns and representations before fine-tuning it for a specific task in post-training.

Another popular training method is unsupervised learning, where models analyze and interpret data without labeled examples.