# What Is The Derivative W.R.T Matrix Calculus You Need For Deep Learning

Where $mathbf{W} in mathcal{R}^{d imes D}$ and $mathbf(x)in mathcal{R}^{d imes 1}$

How to calculate $partial mathbf{Y}/partial mathbf{W}$ ?

Matrix calculus is used in such cases. Your equation looks like it”s from OLS (least squares) theory. In those you differentiate by vector $x$ some quadratic forms like $frac{partial (x”A”Ax)}{partial x}$. Look up relevant formulae in my link above.

Đang xem: Derivative w.r.t matrix

If you really are up to differentiating by matrices not vectors, you”ll end up with tensors. Tensors are fun, but so far I haven”t seem them used a lot in statistics. They”re ubiquitous in physics, btw. Again, follow the link I gave.

Thanks for contributing an answer to Cross Validated!

But avoid

Asking for help, clarification, or responding to other answers.Making statements based on opinion; back them up with references or personal experience.

Use MathJax to format equations. MathJax reference.

See also  Maximum Fi R Data Frame Derivative S Of Fitted Gam Functions — Fderiv

## Not the answer you're looking for? Browse other questions tagged machine-learning optimization derivative matrix-calculus or ask your own question.

Is my step by step derivation of quadratic cost function's (Neural Networks) partial derivative with respect to some weights matrix correct?

site design / logo © 2021 Stack Exchange Inc; user contributions licensed under cc by-sa. rev2021.7.23.39827

Cross Validated works best with JavaScript enabled