How to take matrices as input to neural network?

4 次查看（过去 30 天）

Pritam Ghoshal 2021-6-15

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/856475-how-to-take-matrices-as-input-to-neural-network

回答： Gagan Agarwal 2024-5-27

I have 5000 matrices of size 20x20. How to take these as input to my neural network? Is making a column vector of size 400x1 the only way? Is there some way I can have 20 input features of size 1x20?

7 个评论
显示 5更早的评论隐藏 5更早的评论

Pritam Ghoshal 2021-6-15

For each 20x20 matrix my output will be a 20x1 vector. I have 5000 such matrices.

KSSV 2021-6-15

Yes...you can try for each feature of matrix 1x20 on output ....so each row corresponds to one number of target.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Gagan Agarwal 2024-5-27

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/856475-how-to-take-matrices-as-input-to-neural-network#answer_1463746

Hi Pritam

Yes it is possible and you can try for each feature of matrix to 1x20 on output and that too through various netwroks depending on the nature of your data and what you're trying to achieve.

For instance if:

spatial relationships are crucial, consider CNNs.
sequential relationships matter, look at RNNs or their variants.
you're interested in treating each row/column as a separate entity without focusing on spatial or sequential relationships, the multiple input models or separate input channels approach could work.