Personal website Rudolf Adamkovič

Home / Deep learning / Weight tensor


Ranks

The ranks of the weight tensor are:

  • rank-3 tensor \(W\)
    all weights in the neural network
  • rank-2 matrix \(W^{[i]}\)
    all weights of all neurons in the \(i\)-th layer
  • rank-1 row vector1 \(w^{[i]}_{j}\)
    all weights of the \(j\)-th neuron in the \(i\)-th layer
  • rank-0 scalar \(w^{[i](k)}_{j}\)
    the \(k\)-th weight of the \(j\)-th neuron in the \(i\)-th layer.

Footnotes:

1

\(w^{[i]}_{j}\) is a row vector.


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