公开(公告)号：US20220351055A1

公开(公告)日：2022-11-03

申请号：US17243046

申请日：2021-04-28

Applicant: GE Precision Healthcare LLC

Inventor： Deepa Anand ,  Rakesh Mullick ,  Dattesh Dayanand Shanbhag ,  Marc T. Edgar

IPC: G06N5/04 ,  G06N20/00

Abstract: Systems and techniques that facilitate data diversity visualization and/or quantification for machine learning models are provided. In various embodiments, a processor can access a first dataset and a second dataset, where a machine learning (ML) model is trained on the first dataset. In various instances, the processor can obtain a first set of latent activations generated by the ML model based on the first dataset, and a second set of latent activations generated by the ML model based on the second dataset. In various aspects, the processor can generate a first set of compressed data points based on the first set of latent activations, and a second set of compressed data points based on the second set of latent activations, via dimensionality reduction. In various instances, a diversity component can compute a diversity score based on the first set of compressed data points and second set of compressed data points.