AI Dictionary › AI Fundamentals

Supervised Learning

Apprendimento supervisionato

Supervised learning is the machine learning paradigm where the model learns from labeled examples: for every training input, the correct answer (the "label") is known. The model learns the input-output relationship and applies it to new cases.

Definition

Classic examples: classifying email as spam/not-spam (label: spam yes/no), estimating a house's price (label: actual sale price), recognizing objects in photos (label: object names). It's the most widespread paradigm in traditional business applications.

It differs from unsupervised learning (the model discovers structure in the data without labels, like customer clustering) and from reinforcement learning (learning by trial and error with rewards and penalties). Large language models combine multiple paradigms: self-supervised pre-training on text, followed by refinement with RLHF.

Related terms

• Machine Learning
• Reinforcement Learning
• Training Data
• RLHF
• Deep Learning

More in AI Fundamentals

• LLM (Large Language Model)
• Token
• Context Window
• Temperature
• AI Hallucination
• Fine-tuning
• RAG (Retrieval Augmented Generation)
• Embedding

Put it into practice

• Real scenario: apply this concept with an instant AI verdict.
• Daily gym: short drills to train dictionary concepts.
• Playoff game: challenge other players, elimination-style.

📱 Download the Android app (beta) iOS coming soon

Say what you mean. Get what you need.

Grace Certified, the AI coach that trains and certifies your prompt engineering, by Agora Intelligence.