Abstract: When a data set contains different categories of data and the number of elements contained in the categories differs greatly, we call this type of data set an unbalanced data set. When ...

The problem deals with categorigal data: an underlying assumption is that each data item can be assigned into a certain category. The goal is to be able to deduce, by computational means, the category ...

Using a subset of the extremely popular simple data set MNIST. This data set has many images of handwritten digits 0 to 9. i.e., 10 classes. Each image is of size 28 ×28. In our subset there are 7000 ...