# US 2025/0148374 A1 · Electronic device and control method thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0148374 A1
- Document ID: US20250148374A1
- Status: Published application
- Kind: A1
- Application number: 19/012,155
- Filed: 2025-01-07
- Published: 2025-05-08
- Earliest claimed: 2022-10-17
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Yongkweon JEON; Chungman LEE; Hoyoung KIM
- Web page: https://patentgrep.com/patent/US20250148374A1

## CPC

- G06N 20/00: Machine learning
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0475: Generative networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/08: Learning methods
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An electronic device is provided. The electronic device includes memory storing a learning module comprising a first generator that generates an input vector, a second generator that generates synthetic data, a first learning model that analyzes the synthetic data and one or more computer programs, and one or more processors communicatively coupled to the memory, wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to obtain the input vector from the first generator, obtain the synthetic data corresponding to the input vector through inputting the input vector into the second generator, obtain output data by analyzing the synthetic data by inputting the synthetic data into the first learning model, and learn, at least one parameter included in the first generator and at least one parameter included in the second generator on the basis of the output data.

## Claims

### Claim 1

An electronic device comprising:
memory storing a learning module including a first generator that generates an input vector, a second generator that generates synthetic data, a first learning model that analyzes the synthetic data and one or more computer programs; and
one or more processors communicatively coupled to the memory,
wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to:
obtain the input vector from the first generator,
obtain the synthetic data corresponding to the input vector by inputting the input vector into the second generator,
obtain output data generated by analyzing the synthetic data through inputting the synthetic data into the first learning model, and
learn at least one parameter included in the first generator and at least one parameter included in the second generator on the basis of the output data.

### Claim 2 (depends on 1)

The electronic device of claim 1, wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to:
obtain a loss value on the basis of the output data, and
learn the at least one parameter included in the first generator and the at least one parameter included in the second generator to minimize the loss value.

### Claim 3 (depends on 2)

The electronic device of claim 2, wherein the output data includes statistical feature data of the synthetic data.

### Claim 4 (depends on 3)

The electronic device of claim 3,
wherein the output data includes a mean value and a standard deviation value of the synthetic data, and
wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to:
obtain a first difference value between the mean value of the synthetic data and a mean value of a batch normalization (BN) layer included in the first learning model,
obtain a second difference value between the standard deviation value of the synthetic data and a standard deviation value of the batch normalization (BN) layer included in the first learning model, and
obtain the loss value on the basis of the first difference value and the second difference value.

### Claim 5 (depends on 1)

The electronic device of claim 1,
wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to:
obtain stride data of at least one convolutional layer included in the first learning model; and
replace an identified convolutional layer with a swing convolution layer if the convolutional layer having a stride data size of 2 or more is identified among the at least one convolutional layer, and
wherein the swing convolution layer is a convolutional layer that randomly selects a computation object on the basis of padding data.

### Claim 6 (depends on 5)

The electronic device of claim 5, wherein the swing convolution layer is a layer that includes:
an operation for obtaining second data by adding the padding data to first data if the first data is input thereinto;
an operation for obtaining third data by selecting some data regions from the second data on the basis of a size of the first data; and
an operation for performing convolution computation on the basis of the third data and kernel data of the identified convolutional layer.

### Claim 7 (depends on 1)

The electronic device of claim 1,
wherein the first generator is a generator that generates a latent vector on the basis of at least one parameter, and
wherein the at least one parameter included in the first generator is a parameter used to generate the synthetic data related to a target set by a user.

### Claim 8 (depends on 1)

The electronic device of claim 1, wherein the synthetic data is image data related to a target set by a user.

### Claim 9 (depends on 1)

The electronic device of claim 1,
wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to obtain a second learning model by quantizing the first learning model, and
wherein the second learning model is a compressed model of the first learning model.

### Claim 10 (depends on 9)

The electronic device of claim 9, further comprising:
a communication interface,
wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to transmit the second learning model to an external device through the communication interface.

### Claim 11

A method performed by an electronic device, which stores a learning module including a first generator that generates an input vector, a second generator that generates synthetic data, and a first learning model that analyzes the synthetic data, the method comprising:
obtaining, by the electronic device, the input vector from the first generator;
obtaining, by the electronic device, the synthetic data corresponding to the input vector by inputting the input vector into the second generator;
obtaining, by the electronic device, output data generated by analyzing the synthetic data through inputting the synthetic data into the first learning model; and
learning, by the electronic device, at least one parameter included in the first generator and at least one parameter included in the second generator on the basis of the output data.

### Claim 12 (depends on 11)

The method of claim 11,
wherein in the learning, a loss value is obtained on the basis of the output data, and
wherein the at least one parameter included in the first generator and the at least one parameter included in the second generator are learned to minimize the loss value.

### Claim 13 (depends on 12)

The method of claim 12, wherein the output data includes statistical feature data of the synthetic data.

### Claim 14 (depends on 13)

The method of claim 13,
wherein the output data includes a mean value and a standard deviation value of the synthetic data, and
wherein the obtaining of the loss value includes:
a first difference value between the mean value of the synthetic data and a mean value of a batch normalization (BN) layer included in the first learning model is obtained;
a second difference value between the standard deviation value of the synthetic data and a standard deviation value of the batch normalization (BN) layer included in the first learning model is obtained; and
the loss value is obtained on the basis of the first difference value and the second difference value.

### Claim 15 (depends on 11)

The method of claim 11, further comprising:
obtaining stride data of at least one convolutional layer included in the first learning model; and
replacing an identified convolutional layer with a swing convolution layer if the convolutional layer having a stride data size of 2 or more is identified among the at least one convolutional layer,
wherein the swing convolution layer is a convolutional layer that randomly selects a computation object on the basis of padding data.

### Claim 16 (depends on 15)

The method of claim 15, wherein the swing convolution layer is a layer that includes:
an operation for obtaining second data by adding the padding data to first data if the first data is input thereinto;
an operation for obtaining third data by selecting some data regions from the second data on the basis of a size of the first data; and
an operation for performing convolution computation on the basis of the third data and kernel data of the identified convolutional layer.

### Claim 17 (depends on 16)

The method of claim 16,
wherein the first generator is a generator that generates a latent vector on the basis of at least one parameter, and
wherein the at least one parameter included in the first generator is a parameter used to generate the synthetic data related to a target set by a user.

### Claim 18 (depends on 11)

The method of claim 11, wherein the synthetic data is image data related to a target set by a user.

### Claim 19

One or more non-transitory computer-readable storage media storing a learning module including a first generator that generates an input vector, a second generator that generates synthetic data, a first learning model that analyzes the synthetic data and one or more computer programs including computer-executable instructions that, when executed by one or more processors of an electronic device individually or collectively, cause the electronic device to perform operations, the operations comprising:
obtaining, by the electronic device, the input vector from the first generator;
obtaining, by the electronic device, the synthetic data corresponding to the input vector by inputting the input vector into the second generator;
obtaining, by the electronic device, output data generated by analyzing the synthetic data through inputting the synthetic data into the first learning model; and
learning, by the electronic device, at least one parameter included in the first generator and at least one parameter included in the second generator on the basis of the output data.

### Claim 20 (depends on 19)

The one or more non-transitory computer-readable storage media of claim 19,
wherein in the learning, a loss value is obtained on the basis of the output data, and
wherein the at least one parameter included in the first generator and the at least one parameter included in the second generator are learned to minimize the loss value.
