invariant

Essentially, an ensemble of neurons with mixed selectivity can accommodate many more dimensions of information about a task than a population of neurons with invariant functions.

They focused on an invariant manifold, termed as the DA manifold, and conducted a stability analysis.

"They have learned to be invariant to these particular dimensions in the stimulus space, and it's model-specific, so other models don't have those same invariances."

We get universal power laws, and the system is scale invariant: if you take a photograph of the fluid flowing through the pores and blow it up, it looks like the original.

In particular, both theories were scale invariant, meaning the physics of the systems the theories described didn’t change as the systems got larger or smaller.