This is true. I think that visualising points on a (hyper-)sphere is fine, but it is difficult in practice to parametrise the points that way.
It is more that the vectors on the gpu look like Rn, but the vectors in the model are treated more like R×Sn−1
This is true. I think that visualising points on a (hyper-)sphere is fine, but it is difficult in practice to parametrise the points that way.
It is more that the vectors on the gpu look like Rn, but the vectors in the model are treated more like R×Sn−1