公开(公告)号：US20230409673A1

公开(公告)日：2023-12-21

申请号：US17807761

申请日：2022-06-20

Applicant: GE Precision Healthcare LLC

Inventor： Ravishankar Hariharan ,  Rohan Keshav Patil ,  Rahul Venkataramani ,  Prasad Sudhakara Murthy ,  Deepa Anand ,  Utkarsh Agrawal

IPC: G06K9/62 ,  G06N3/02

CPC classification number: G06K9/6265 ,  G06K9/6227 ,  G06N3/02

Abstract: Systems/techniques that facilitate improved uncertainty scoring for neural networks via stochastic weight perturbations are provided. In various embodiments, a system can access a trained neural network and/or a data candidate on which the trained neural network is to be executed. In various aspects, the system can generate an uncertainty indicator representing how confidently executable or how unconfidently executable the trained neural network is with respect to the data candidate, based on a set of perturbed instantiations of the trained neural network.