Compression of deep convolutional neural network using additional importance-weight-based filter pruning approach

HIGHLIGHTS

  • who: Shrutika S. Sawant et al. from the Institute for Integrated Circuits, Erlangen, Germany CIML Group, Biophysics, University Regensburg, Regensburg, Germany have published the Article: Compression of Deep Convolutional Neural Network Using Additional Importance-Weight-Based Filter Pruning Approach, in the Journal: (JOURNAL)
  • what: In this Article a filter pruning method a process discarding a subset unimportant or weak filters from the original CNN model is proposed which alleviates the shortcomings over-sized CNN architectures at the cost storage space and time. The authors show that the performance the pruned CNN model is very similar . . .

     

    Logo ScioWire Beta black

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

    Thanks :)

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

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?