AI Dictionary › Fondamenti AI

Vector

Vettore

A vector, in the context of artificial intelligence, is an ordered sequence of numbers used to mathematically represent a piece of information: a word, an image, a user, a concept. Each number in the sequence is a "dimension" of the vector, and the set of all dimensions defines a point in a multidimensional mathematical space.

Definition

How it works

Neural networks operate by transforming vectors into other vectors through multiplications by parameter matrices and non-linear functions. The distance or angle between two vectors in this space can be interpreted as a measure of how similar the information they represent is: nearby vectors tend to represent related concepts.

Applications

It is the basic unit with which every type of data is represented internally by an artificial intelligence model: a token becomes a vector through the embedding layer, an image becomes a vector of extracted features, an entire document can be summarized into a single vector used for semantic search in a vector database.

History & etymology

The term is inherited directly from linear algebra, the branch of mathematics that studies these objects and their transformations, and it became central to machine learning as models began representing every type of data in continuous numerical form rather than symbolic form.

Related terms

• Embedding
• Weight Matrix
• Vector database
• Semantic search
• Embedding Layer

More in Fondamenti AI

• 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.