Today's article comes from the journal of Machine Learning Science and Technology. The authors are Watts et al., from the University of Manchester, in the United Kingdom. In this paper they create a new "bound" on amplification. That is: an upper limit on just how-much synthetic information can be safely generated from an existing dataset.
You must be an active Journal Club member to access this content. If you're already a member, click the blue button to login. If you're not a member yet, click the sign-up button to get started.
Login to My Account
Sign Up