Matlab Neural Net Pattern Recognition: Why does the Neural Net uses Features as inputs instead of samples?

For example: Wine Classification

wineInputs - a 13x178 matrix of thirteen attributes of 178 wines.

1. Alcohol, 2. Malic acid, 3. Ash, 4. Alcalinity of ash, 5. Magnesium, 6. Total phenols, 7. Flavanoids, 8. Nonflavanoid phenols,9. Proanthocyanins, 10. Color intensity

11. Hue, 12. OD280/OD315 of diluted wines, 13. Proline

--------> That means 13 attributes are the features and 178 wines are samples.

wineTargets - a 3x178 matrix of 7200 associated class vectors

defining which of three classes each input is assigned to. Classes

are represented by a 1 in row 1, 2 or 3.

1. Vinyard #1, 2. Vinyard #2, 3. Vinyard #3

------------------>That means 3 are the labels!

The Matlab Neural Net Pattern Recognition uses the 13 features/attributes as Input and 3 labels as outputs.

But why does the tool uses 13 features as inputs instead of 178 wines/samples?

Answer 1

[Shivang Srivastava]

As per my understanding you wanted to know why in the wine classification example is the input of size [features, samples].

To use the train function the input is given of the size [features, samples] unlike the popular format of size [samples, features].

You can refer to train function documentation for more information.