Title:
SYSTEMS AND METHODS FOR ON-DEVICE VALIDATION OF A NEURAL NETWORK MODEL
Document Type and Number:
WIPO Patent Application WO/2024/080521
Kind Code:
A1
Abstract:
A method for validating a trained artificial intelligence (AI) model on a device is provided. The method includes deploying a validation model generated by applying a plurality of anticipated configurational changes associated with the trained AI model requiring validation. Further, the method includes providing input data to each of the validation model and the trained AI model for receiving an output from each of the validation model and the trained AI model, wherein the output of the validation model is further based on one or more actual configurational deviations that occurred during training of the trained AI model since deployment of the trained AI model on the device. Furthermore, the method includes combining the output of each of the validation model and the trained AI model to validate the trained AI model.
Inventors:
M GOKULKRISHNA (IN)
SACHITHANANDAM SIVA KAILASH (IN)
R PRASANNA (IN)
SOANS RAJATH ELIAS (IN)
SENAPATI ALLADI ASHOK KUMAR (IN)
NAIDU PRAVEEN DORESWAMY (IN)
NELAHONNE SHIVAMURTHAPPA PRADEEP (IN)
SACHITHANANDAM SIVA KAILASH (IN)
R PRASANNA (IN)
SOANS RAJATH ELIAS (IN)
SENAPATI ALLADI ASHOK KUMAR (IN)
NAIDU PRAVEEN DORESWAMY (IN)
NELAHONNE SHIVAMURTHAPPA PRADEEP (IN)
Application Number:
PCT/KR2023/011844
Publication Date:
April 18, 2024
Filing Date:
August 10, 2023
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06N3/08; G06N3/04
Foreign References:
| US20220300820A1 | 2022-09-22 | |||
| US20170024642A1 | 2017-01-26 | |||
| US11468383B1 | 2022-10-11 | |||
| US20220309389A1 | 2022-09-29 | |||
| US10754764B2 | 2020-08-25 |
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF: