O'Reilly logo
  • Tan Duong thinks this is interesting:

More generally, you can take the dot product between higher-dimensional tensors, following the same rules for shape compatibility as outlined earlier for the 2D case:

From

Cover of Deep Learning with Python

Note

(a, b, ..., d_compatiple) . (d_compatiple, ..., x, y, z) -> (a, b, ..., x, y, z)

d_compatiple will gone.