On Mon, Apr 19, 2021, 5:02 PM Jim Bromer <[email protected]> wrote:
> That use of the term "vector" is confusing. But, in my opinion it is also > sometimes used pretentiously. > I use it mathematically. A vector is an array of numbers. In a typical neural network the direction of an input or an output to a > node is not encoded in the input or output itself. > A vector is not a direction or a point in space, although those are two things that you can represent with vectors. We can also represent the states of neurons with vectors. We do that because it simplifies notation, not because we want to be elite by using a secret language. When you add vectors or matrices (2-D arrays) you add their elements. When you multiply (dot product) vectors, you multiply their elements and add them up. When you multiply matrices, you form a new matrix where each element is a dot product of a row from the first matrix and a column from the second. There is a lot more to linear algebra but that's a start. > > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T68be2fedf1f53ef2-M4746fd9c86a86b1e92e5b5e7 Delivery options: https://agi.topicbox.com/groups/agi/subscription
