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:
- Chapter 2. Before we begin: the mathematical building blocks of neural networks
- from Deep Learning with Python
- Publisher: Manning Publications
- Released: December 2017
(a, b, ..., d_compatiple) . (d_compatiple, ..., x, y, z) -> (a, b, ..., x, y, z)
d_compatiple will gone.
Share this highlighthttp://www.safaribooksonline.com/a/deep-learning-with/14577769/