106
edits
Tensor rank: Difference between revisions
→Rank of Common Tensors in Machine Learning
SpamFighter (talk | contribs) No edit summary |
SpamFighter (talk | contribs) |
||
| Line 2: | Line 2: | ||
The rank of a [[tensor]], also known as its ''order'', refers to the number of dimensions or indices required to describe the tensor. Formally, the tensor rank is defined as the number of axes within a tensor. In other words, the tensor rank determines the complexity of the data structure, providing insights into the nature of the underlying data. | The rank of a [[tensor]], also known as its ''order'', refers to the number of dimensions or indices required to describe the tensor. Formally, the tensor rank is defined as the number of axes within a tensor. In other words, the tensor rank determines the complexity of the data structure, providing insights into the nature of the underlying data. | ||
==Rank of | ==Rank of common tensors in machine learning== | ||
===Scalar=== | ===Scalar=== | ||
A scalar, also known as a rank-0 tensor, is a single numerical value with no dimensions. Scalars are typically used to represent simple quantities such as a learning rate or a loss value in machine learning algorithms. | A scalar, also known as a rank-0 tensor, is a single numerical value with no dimensions. Scalars are typically used to represent simple quantities such as a learning rate or a loss value in machine learning algorithms. | ||