Tensor
Also: tensors
A grid of numbers (a table, or a stack of tables). Everything inside a model is stored and calculated as tensors.
The fuller definition
A tensor is a numerical array with a defined shape. Vectors, matrices, and higher-dimensional arrays are tensors used to represent data and model calculations.
Lines represent computational connections with learned values. This tiny diagram illustrates a neural network; a transformer or mixture-of-experts model has additional structures not shown here.
A concrete example
A table of token vectors can have one dimension for token positions and another for embedding values.
The distinction that matters
A tensor is a data structure, not a separate intelligent component.
Related terms
Embedding
A list of numbers used to compare items such as texts. Texts with similar meanings may have similar lists.
FoundationsNeural network
A model made of linked layers of maths. Training adjusts its numbers so it can learn patterns from data.
Hardware & hostingGPU — Graphics processing unit
The chip that handles graphics, and also the maths AI needs. It is what makes AI fast.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.