US 12,602,749 B2 · Parameter optimizing method of neural network and computing apparatus

Abstract

A parameter optimizing method of a neural network and a computing apparatus are provided. A shared filter is obtained, and the shared filter includes multiple shared weights. Those shared weights are assigned to multiple sub-filters. Each sub-filter corresponds to one of multiple channels. Each sub-filter includes multiple sub-weights. The size of each sub-filter is smaller than or equal to the size of the shared filter. The sub-weights of each sub-filter are generated according to the assigned shared weight. The sub-filters of those channels are used to be computed with one or more pieces of input data respectively. Thereby, checkerboard artifacts may be reduced or avoided.

Claims22

Dependent claims

A parameter optimizing method of a neural network, comprising:

obtaining a shared filter, wherein the shared filter comprises a plurality of shared weights;
assigning the shared weights to a plurality of sub-filters, wherein each of the sub-filters corresponds to one of a plurality of channels, each of the sub-filters comprises a plurality of sub-weights, and a size of each of the sub-filters is smaller than or equal to a size of the shared filter;
generating the sub-weights of each of the sub-filters according to assigned shared weights;
and
performing a computation with at least one input data by using the sub-filters of the channels respectively.

2 more elements

A computing apparatus, comprising:

a storage configured to store a program code;
and
a processor coupled to the storage and configured to load and execute the program code to:
obtain a shared filter, wherein the shared filter comprises a plurality of shared weights;
assign the shared weights to a plurality of sub-filters, wherein each of the sub-filters corresponds to one of a plurality of channels, each of the sub-filters comprises a plurality of sub-weights, and a size of each of the sub-filters is smaller than or equal to a size of the shared filter;
generate the sub-weights of each of the sub-filters according to the assigned shared weights;
and
perform a computation with at least one input data by using the sub-filters of the channels respectively.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application

18/408,601Filed 10 Jan 2024 · us provisional application

Priority

TW 11213921313 Oct 2023

Published

US 2024/0296520 A15 Sep 2024

Granted

14 Apr 2026

Term ends

Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06T 5/60
Image enhancement or restoration: using machine learning, e.g. neural networks
G06T 2207/20016
Special algorithmic details: hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
G06T 2207/20081
Special algorithmic details: training; Learning
G06T 2207/20084
Special algorithmic details: artificial neural networks [ANN]

Parameter optimizing method of neural network and computing apparatus

Life of this patent

Parameter optimizing method of neural network and computing apparatus

Life of this patent

Abstract

Claims22