# US 2026/0073219 A1 · Electronic device and method for pruning a neural network

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

- Number: US 2026/0073219 A1
- Document ID: US20260073219A1
- Status: Published application
- Kind: A1
- Application number: 19/214,684
- Filed: 2025-05-21
- Published: 2026-03-12
- Earliest claimed: 2024-09-11
- Assignees: Hyundai Motor Company; Kia Corporation
- Applicants: Hyundai Motor Company; Kia Corporation
- Inventors: Won Seok Jeon; Ju Young Yang; Byeong Wook Jeon
- Web page: https://patentgrep.com/patent/US20260073219A1

## CPC

- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An electronic device includes a memory storing computer-executable instructions and at least one processor coupled to the memory and configured to execute the computer-readable instructions. The at least one processor is configured to identify a merge layer included in a pruning target model of a neural network to determine a target group including layers, including the merge layer and a sub-layer logically connected with the merge layer. The at least one processor is configured to apply a learnable parameter to each of the layers included in the target group. The at least one processor is configured updates the learnable parameter through propagation of the pruning target model. The at least one processor is configured to perform pruning of the pruning target model based on the updated learnable parameter.

## Claims

### Claim 1

An electronic device, comprising:
a memory storing computer-readable instructions; and
at least one processor coupled to the memory, the at least one processor configured to execute the computer-readable instructions to:
identify a merge layer included in a pruning target model of a neural network to determine layers, including a target group including the merge layer and a sub-layer logically connected with the merge layer;
apply a learnable parameter to each of the layers included in the target group;
update the learnable parameter through propagation of the pruning target model; and
perform pruning of the pruning target model, to generate a pruned target model, based on the updated learnable parameter.

### Claim 2 (depends on 1)

The electronic device of claim 1, wherein the at least one processor is configured to identify the merge layer based on a computational graph of the pruning target model.

### Claim 3 (depends on 1)

The electronic device of claim 1, wherein the at least one processor is configured to:
apply the learnable parameter to the merge layer to obtain a pruning merge layer; and
apply the learnable parameter to the sub-layer to obtain a pruning sub-layer.

### Claim 4 (depends on 3)

The electronic device of claim 3, wherein the at least one processor is configured to:
replace the merge layer of the pruning target model with the pruning merge layer; and
replace the sub-layer of the pruning target model with the pruning sub-layer.

### Claim 5 (depends on 4)

The electronic device of claim 4, wherein the at least one processor is configured to:
forward propagate and back propagate the pruning target model including the pruning merge layer and the pruning sub-layer to obtain a loss; and
update the learnable parameter based on the loss to which a predetermined regularization term is applied.

### Claim 6 (depends on 5)

The electronic device of claim 5, wherein the at least one processor is configured to:
determine a skip layer to be excluded from the pruning target model, among the layers included in the target group, based on the updated learnable parameter; and
change values included in the skip layer in the pruning target model to a predetermined value to perform pruning of the pruning target model.

### Claim 7 (depends on 1)

The electronic device of claim 1, wherein the at least one processor is configured to update the layers included in the target group through propagation of the pruned target model.

### Claim 8 (depends on 7)

The electronic device of claim 7, wherein the at least one processor is configured to:
determine whether the pruning target model in which the layers included in the target group are updated satisfies a predetermined converge criterion; and
perform pruning of the pruning target model by applying the learnable parameter to each of the layers included in the target group, based on determining that the pruning target model does not satisfy the predetermined converge criterion.

### Claim 9 (depends on 1)

The electronic device of claim 1, wherein the at least one processor is configured to:
apply mobility data to the pruned target model to obtain an output; and
apply the output to a mobility system to control the mobility system.

### Claim 10

A method, comprising:
identifying a merge layer included in a pruning target model of a neural network to determine a target group including layers, including the merge layer and a sub-layer logically connected with the merge layer;
applying a learnable parameter to each of the layers included in the target group;
updating the learnable parameter through propagation of the pruning target model; and
performing pruning of the pruning target model, to generate a pruned target model, based on the updated learnable parameter.

### Claim 11 (depends on 10)

The method of claim 10, wherein determining the target group includes identifying the merge layer based on a computational graph of the pruning target model.

### Claim 12 (depends on 10)

The method of claim 10, wherein performing pruning of the pruning target model includes:
applying the learnable parameter to the merge layer to obtain a pruning merge layer; and
applying the learnable parameter to the sub-layer to obtain a pruning sub-layer.

### Claim 13 (depends on 12)

The method of claim 12, wherein performing pruning of the pruning target model includes:
replacing the merge layer of the pruning target model with the pruning merge layer; and
replacing the sub-layer of the pruning target model with the pruning sub-layer.

### Claim 14 (depends on 13)

The method of claim 13, wherein performing pruning of the pruning target model includes:
forward propagating and back propagating the pruning target model including the pruning merge layer and the pruning sub-layer to obtain a loss; and
updating the learnable parameter based on the loss to which a predetermined regularization term is applied.

### Claim 15 (depends on 14)

The method of claim 14, wherein performing pruning of the pruning target model includes:
determining a skip layer to be excluded from the pruning target model among the layers included in the target group, based on the updated learnable parameter; and
changing values included in the skip layer in the pruning target model to a predetermined value to perform the pruning of the pruning target model.

### Claim 16 (depends on 10)

The method of claim 10, further comprising updating the layers included in the target group through propagation of the pruned target model.

### Claim 17 (depends on 16)

The method of claim 16, wherein updating the layers included in the target group includes:
determining whether the pruning target model in which the layers included in the target group are updated satisfies a predetermined converge criterion; and
performing pruning of the pruning target model by applying the learnable parameter to each of the layers included in the target group, based on determining that the pruning target model does not satisfy the predetermined converge criterion.

### Claim 18 (depends on 10)

The method of claim 10, further comprising:
applying mobility data to the pruned target model to obtain an output; and
applying the output to a mobility system to control the mobility system.
