- Patent Title: System and method for noise-based training of a prediction model
-
Application No.: US16785957Application Date: 2020-02-10
-
Publication No.: US10997501B2Publication Date: 2021-05-04
- Inventor: Bob Sueh-chien Hu , Joseph Yitang Cheng
- Applicant: Aivitae LLC
- Applicant Address: US CA Redwood City
- Assignee: Aivitae LLC
- Current Assignee: Aivitae LLC
- Current Assignee Address: US CA Redwood City
- Agency: Pillsbury Winthrop Shaw Pittman LLP
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06T11/00 ; G06T7/00 ; G06T5/00

Abstract:
In some embodiments, noise data may be used to train a neural network (or other prediction model). In some embodiments, input noise data may be obtained and provided to a prediction model to obtain an output related to the input noise data (e.g., the output being a prediction related to the input noise data). One or more target output indications may be provided as reference feedback to the prediction model to update one or more portions of the prediction model, wherein the one or more portions of the prediction model are updated based on the related output and the target indications. Subsequent to the portions of the prediction model being updated, a data item may be provided to the prediction model to obtain a prediction related to the data item (e.g., a different version of the data item, a location of an aspect in the data item, etc.).
Public/Granted literature
- US20200175368A1 SYSTEM AND METHOD FOR NOISE-BASED TRAINING OF A PREDICTION MODEL Public/Granted day:2020-06-04
Information query