Analysis of spatial filtering in neural spatiospectral filters and its dependence on training target characteristics

HIGHLIGHTS

• What: In this contribution the authors propose a framework to analyze neural spatiospectral filters (NSSFs) with respect to their capabilities to extract represent spatial information. Using two conceptually different NSSFs as example the authors show that not all NSSFs use spatial information under all circumstances that the training target signal has a significant influence on the spatial filtering behavior of an NSSF. Unlike explainable AI approaches that focus on the system behavior for specific classes of signals, e_g_[25, 26], the goal of this contribution is to advance the understanding of the signal processing capabilities of ANNs . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.