seems that the description of example iris_dataset in nprtool is wrong

 irisInputs - a *4x150* matrix of four attributes of *1000* flowers.
 irisTargets - a *3x150* matrix of *1000* associated class vectors
    defining which of *four* classes each input is assigned to.  Classes
    are represented by a 1 in one of *four* rows, with zeros in the others.

maybe it should be 4 attributes of 150 flowers. 3 classes

Answer 1

[Fei Deng]

Hi Ryant, which specific page are you referring to and what MATLAB release are you using?

For the iris_dataset data, yes you are right, irisTargets is a 3x150 matrix of associated class vectors defining which of the three classes each input is assigned to, as documented here:

https://www.mathworks.com/help/releases/R2016a/nnet/ref/trainsoftmaxlayer.html?searchHighlight=trainSoftmaxLayer

where you can find:

Examples

Classify Using Softmax Layer

Load the sample data.

[X,T] = iris_dataset;

X is a 4x150 matrix of four attributes of iris flowers: Sepal length, sepal width, petal length, petal width.

T is a 3x150 matrix of associated class vectors defining which of the three classes each input is assigned to. Each row corresponds to a dummy variable representing one of the iris species (classes). In each column, a 1 in one of the three rows represents the class that particular sample (observation or example) belongs to. There is a zero in the rows for the other classes that the observation does not belong to.

[Nav I]

@Fei: Just like Ryant, even I feel the description is wrong. Why is it mentioned as 1000 class vectors when it should be 150? Why is it mentioned as 1000 flowers with 4 attributes. Basically, what is the 1000 for?

[Nav I]

Could it be that for creating the dataset of 150 flowers, there were a thousand flowers sampled? Is that what it means or is it something else?