Clear Filters
Clear Filters

How to take matrices as input to neural network?

17 views (last 30 days)
Pritam Ghoshal
Pritam Ghoshal on 15 Jun 2021
Answered: Gagan Agarwal on 27 May 2024 at 7:29
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 Comments
Pritam Ghoshal
Pritam Ghoshal on 15 Jun 2021
For each 20x20 matrix my output will be a 20x1 vector. I have 5000 such matrices.
KSSV
KSSV on 15 Jun 2021
Yes...you can try for each feature of matrix 1x20 on output ....so each row corresponds to one number of target.

Sign in to comment.

Answers (1)

Gagan Agarwal
Gagan Agarwal on 27 May 2024 at 7:29
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.

Products


Release

R2020b

Community Treasure Hunt

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

Start Hunting!