Jacobin matrix of the NN's output respect to the input

2 次查看（过去 30 天）
Yunshen Huang
Yunshen Huang 2020-2-19
回答： Pan Zhao 2021-11-8
Hi all,
Is there a convenient built-in funciton for the NN can get me the Jacobin matrix of output respect to input? For instance, # input (feature) = 4, # output = 3. Then this function gives me a 3*4 matrix.
I found one called defaultderiv, but this gives the Jacobian of errors with respect to the net's weights and biases, which is not what I want.
Even though, by knowing the weights, biases, active function, I could form a symbolic equation fed into jacobin( ) function to obatin what I need. But it seems a bit messy.
Thanks for your answer

请先登录，再回答此问题。

回答（2 个）

Nikhil Sonavane
Nikhil Sonavane 2020-4-20
There is a function to compute the jacobian of a matrix. You may refer to its documentation for more details.
Pan Zhao
Pan Zhao 2021-11-8
Hi Yunshen, have you found a solution?

类别

在 Help Center 和 File Exchange 中查找有关 Parameterization Methods 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by