Information bottleneck theory based exploration of cascade learning

HIGHLIGHTS

• who: Xin Du and colleagues from the School of Electronics and Computer Science, University of Southampton, Southampton , AS, UK have published the research: Information Bottleneck Theory Based Exploration of Cascade Learning, in the Journal: Entropy 2021, 23, 1360. of /2021/
• what: The authors evaluate this effect by proposing an information transition ratio I(T; Y)/I(X; T) and show that it can serve as a useful heuristic in setting the depth of a neural network that achieves satisfactory accuracy of classification. The work, done in an era of hardware limitations, focuses on data reduction . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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