公开(公告)号：US20210390400A1

公开(公告)日：2021-12-16

申请号：US17304163

申请日：2021-06-15

Applicant: SRI International

Inventor： Yi Yao ,  Ajay Divakaran ,  Hammad A. Ayyubi

IPC: G06N3/08 ,  G06F17/13 ,  G06K9/62

Abstract: Techniques are described for neural networks based on Progressive Neural ODEs (PODEs). In an example, a method to progressively train a neural ordinary differential equation (NODE) model comprises processing, by a machine learning system executed by a computing system, first training data, the first training data having a first complexity, to perform training of a first layer for the NODE model; and after performing the first training, processing second training data, the second training data having a second complexity that is higher than the first complexity, to perform training of a second layer for the NODE model.