How to train a Matlab Neural Network using matrices as inputs?

Vimukthi Weerasiri

2016 1 月 5

1 回答

回答採用済み

3 ビュー (30 日間)

0 投票

I am making 8 x 8 tiles of Images and I want to train a RBF Neural Network in Matlab using those tiles as inputs. I understand that I can convert the matrix into a vector and use it. But is there a way to train them as matrices? (to preserve the locality) Or is there any other technique to solve this problem?

1 件のコメント
-1 件の古いコメントを表示 -1 件の古いコメントを非表示

Sivakumaran Chandrasekaran 2016 年 1 月 5 日

in MATLAB, if you write y=1.. is also a MATRIX.. you can also train them as matrices

サインインしてコメントする。

サインインしてこの質問に回答する。

Follow Question

採用された回答

Greg Heath 2016 年 1 月 6 日

0 投票

Standard procedure:

Each input and output must be a column vector. If your original input is an image, just use the column operator x = image(:). However, if you wish to consider several images, each image will be a column in the network's input matrix.

No biggie

Hope this helps.

Thank you for formally accepting my answer

Greg