Currently using the heatmap approach we can see some basic success from the tensor decomposition (word documents are classified with word docs, malware is classified with malware), however we can do better.
This probably starts at rethinking the construction of our tensor. How should we best represent this data as a tensor?
We might also be able to do a 4th order tensor, a list of third order tensors that encompass multiple different constructions.
Currently using the heatmap approach we can see some basic success from the tensor decomposition (word documents are classified with word docs, malware is classified with malware), however we can do better.
This probably starts at rethinking the construction of our tensor. How should we best represent this data as a tensor?
We might also be able to do a 4th order tensor, a list of third order tensors that encompass multiple different constructions.