Enhancing convolutional neural networks via separately trained kernels for digit recognition

HIGHLIGHTS

  • What: In this section, this paper presents the results obtained from the experiments conducted using the methodology described in the previous section. The primary focus of the analysis is the comparison of the performance of the comprehensively trained model with pre-trained convolutional kernels and a conventional model with randomly initialized convolutional kernels of the same architecture. The promising results obtained in this study provide a strong foundation for further exploration.
  • Who: Zhaochen Yang from the Department of Computing, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, China have published the research work . . .

     

    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 ?