Patent · US Active

Generating training datasets for training neural networks

US11907675B2 · kind B2 · utility

0Cited by

0References

17Claims

0Family size

Assignee

Uber Technologies, Inc. · US

Inventors

Felipe Petroski Such · Rochester, US
Aditya Rawal · New Delhi, IN
Joel Anthony Lehman · San Francisco, US
Kenneth O. Stanley · San Francisco, US
Jeffrey Michael Clune · San Francisco, US

Key dates

Filing date	Jan 17, 2020
Grant date	Feb 20, 2024
Priority date	—
Expiry date	Mar 26, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/047
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A generative cooperative network (GCN) comprises a dataset generator model and a learner model. The dataset generator model generates training datasets used to train the learner model. The trained learner model is evaluated according to a reference training dataset. The dataset generator model is modified according to the evaluation. The training datasets, the dataset generator model, and the leaner model are stored by the GCN. The trained learner model is configured to receive input and to generate output based on the input.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.