Personal website Rudolf Adamkovič

Home / Deep learning


Target matrix

A matrix with training targets 1, as a rank-2 tensor:

\begin{equation*} Y = \begin{pmatrix} \vphantom{\Big(} \vec{y}^1 & \cdots & \vec{y}^m \end{pmatrix} = \begin{pmatrix} y_1^1 & \cdots & y_1^m \\ \vdots & \ddots & \vdots \\ y_n^1 & \cdots & y_n^m \end{pmatrix} \in \mathbb{R}^{n \times m} \end{equation*}

where

  • \(x^i\) is the \(i\)-th target
  • \(x^i_j\) is the \(j\)-th target of the \(i\)-th example

and

  • \(m\) is the number of examples
  • \(n\) is the number of targets.

Footnotes:

1

Targets for all examples in the corresponding input matrix.


© 2025 Rudolf Adamkovič under GNU General Public License version 3.
Made with Emacs and secret alien technologies of yesteryear.