It sounds like a misnomer to me. I probably will just call it a “vector” representation. It doesn’t have the “distributed” meaning of scattering information into different places. For example, to recognize a cat with “distributed” representation, we may distribute features into like “does it has a tail?”, “does it have four legs?”, and “does it has pointy ears?”. Each of these features can be considered as a component in a vector. And thus the overall vector will have exponentially more expressive power than a scalar (non-distributed) representation.
Distributed representation
Posted on