Skip to content

Model Training & Adaptation

Tensor

An organized collection of numbers used by AI, from a single number to tables and more complex arrangements.

Example

An image is represented as numbers arranged by height, width and color channel.

Why people use it

It gives AI software a way to organize numbers used in its calculations.

What you'll hear

“What does each dimension of this array represent?”

What this means for you

Focus on what each dimension represents in the particular application.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Can an ordinary spreadsheet hold some of the same kinds of numbers?
Yes. A table is one simple arrangement; AI may also need numbers organized across additional directions.
Does having more dimensions make AI smarter?
No. Dimensions describe how numbers are organized, rather than the quality of the AI using them.
Are dimensions always physical directions?
No. They can represent things such as examples, words or color channels.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice