Stochastic surprisal: an inferential measurement of free energy in neural networks

HIGHLIGHTS

• who: Mohit Prabhushankar from the University of Westminster, United Kingdom have published the research work: Stochastic surprisal: An inferential measurement of free energy in neural networks, in the Journal: (JOURNAL)
• what: The authors evaluate stochastic surprisal on two applications including image_quality assessment and robust object recognition. In image_quality assessment, the authors evaluate the technique to assess the quality of distorted images at different levels of distortions. The authors propose a concept that is able to assess the noise characteristics in images to assign objective quality, as well as ignore the same noise characteristics to robustly . . .
  

   

  

  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.