I think that since the input to a node (in a NN) can consist of multiple
scalars, it is sometimes called a vector. However, it is by no means certain
that the use of the term is appropriate. From Wikipedia
Tuples that are not really vectors[edit
<https://en.wikipedia.org/w/index.php?title=Vector_(mathematics_and_physics)&action=edit§ion=4>]
The set \mathbb {R} ^{n}
of tuples <https://en.wikipedia.org/wiki/Tuple> of *n* real numbers has a
natural structure of vector space defined by component-wise addition and scalar
multiplication <https://en.wikipedia.org/wiki/Scalar_multiplication>. When such
tuples are used for representing some data, it is common to call them
*vectors*, even if the vector addition does not mean anything for these data,
which may make the terminology confusing.
And I am not seeing how the operation applied to the tuple that is input to the
node and the node can be called matrix multiplication or addition. I might be
wrong but I would be surprised if I was.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T68be2fedf1f53ef2-M49f3123aef62950864c75b50
Delivery options: https://agi.topicbox.com/groups/agi/subscription
