dense feature
A feature in which most or all values are nonzero, typically a Tensor of floating-point values.
Plain English Explanation
A feature in which most or all values are nonzero, typically a Tensor of floating-point values. For example, the following 10-element Tensor is dense because 9 of its values are nonzero: 7 4 9 | 6 | --- --- --- | --- | Contrast with sparse feature.
How is it used?
Practitioners refer to dense feature when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.