Invention Publication
- Patent Title: APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT FOR OPTIMIZING PARAMETERS OF A COMPRESSED REPRESENTATION OF A NEURAL NETWORK
-
Application No.: US18001987Application Date: 2021-06-11
-
Publication No.: US20230269387A1Publication Date: 2023-08-24
- Inventor: Francesco CRICRÌ , Hamed REZAZADEGAN TAVAKOLI , Honglei ZHANG , Nannan ZOU
- Applicant: Nokia Technologies Oy
- Applicant Address: FI Espoo
- Assignee: Nokia Technologies Oy
- Current Assignee: Nokia Technologies Oy
- Current Assignee Address: FI Espoo
- International Application: PCT/IB2021/055178 2021.06.11
- Date entered country: 2022-12-15
- Main IPC: H04N19/42
- IPC: H04N19/42 ; H04N19/124 ; H04N19/176 ; G06N3/0455 ; G06N3/0985

Abstract:
In example embodiments, an apparatus, a method, and a computer program product are provided. An example apparatus include processing circuitry; and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processing circuitry, cause the apparatus at least to: overfit a neural network on each media item, from a batch of media items, for a number of iterations to obtain an overfitted neural network model for the each media item; evaluate the overfitted neural network model on the each media item to obtain evaluation errors; and update parameters of the neural network to be based on the evaluation errors.
Information query