tensor

A tensor is a multidimensional numerical array used to represent inputs, weights and intermediate results in AI models.

1 articleLast mentioned

In machine learning, a tensor is a numerical array organized along one or more axes. A single number, vector and matrix can be treated as zero-, one- and two-dimensional tensors, respectively. Models also represent inputs, weights and intermediate results with higher-dimensional tensors.

In mathematics, a tensor has a more precise definition based on how it transforms when coordinates change. Machine learning usage generally emphasizes multidimensional arrays and operations on them.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • ShapeLearn Qwen3.8-27B on a 16GB GPU: Agent Tests Pass 4 of 5 at 128k ContextAI Performance ·

    ShapeLearn's approach is to learn the ideal data type for each tensor individually rather than applying one scheme across the whole model, which ByteShape says…

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.