# US 2025/0094801 A1 · Neural network critical neuron selection

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

- Number: US 2025/0094801 A1
- Document ID: US20250094801A1
- Status: Published application
- Kind: A1
- Application number: 18/889,828
- Filed: 2024-09-19
- Published: 2025-03-20
- Earliest claimed: 2023-09-20
- Assignees: Entanglement, Inc.
- Applicants: Entanglement, Inc.
- Inventors: Amit VERMA
- Web page: https://patentgrep.com/patent/US20250094801A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure relates to systems and methods for optimizing neural networks by strategically identifying and pruning critical neurons to reduce computational resources while maintaining high levels of accuracy. The method involves determining critical neurons within a neural network based on features collected during an initial phase of training. These critical neurons are then pruned from the network, resulting in a pruned neural network with the critical neurons removed. The training process continues using the pruned neural network, allowing for significant computational savings without substantially impacting the network's performance.

## Claims

### Claim 1

A method comprising:
determining critical neurons in a neural network;
pruning the critical neurons from the neural network, wherein the pruning generates a pruned neural network with the critical neurons removed; and
continuing a training process using the pruned neural network.

### Claim 2 (depends on 1)

The method of claim 1, further comprising determining an early stop point during the training of the neural network.

### Claim 3 (depends on 2)

The method of claim 2, wherein the early stop point comprises a subset of a training data set.

### Claim 4 (depends on 3)

The method of claim 3, wherein initial phases of the training process train the neural network using the subset of training data before the early stop point.

### Claim 5 (depends on 3)

The method of claim 3, wherein continuing the training process comprises training the neural network using a remaining subset of training data after the early stop point.

### Claim 6 (depends on 1)

The method of claim 1, wherein the pruning of the critical neurons is implemented globally.

### Claim 7 (depends on 1)

The method of claim 1, wherein the pruning of the critical neurons is implemented layer-wise.

### Claim 8

A critical neuron pruning system comprising:
a memory; and
a processor that is configured to execute machine readable instructions stored in the memory for causing the processor to:
determine critical neurons in a neural network;
prune the critical neurons from the neural network, wherein the pruning generates a pruned neural network with the critical neurons removed; and
continue a training process using the pruned neural network.

### Claim 9 (depends on 8)

The critical neuron pruning system of claim 8, wherein the system receives a pruning rate parameter.

### Claim 10 (depends on 9)

The critical neuron pruning system of claim 9, wherein the system determines a number of critical neurons for a layer of the network based on the pruning rate parameter and a total number of neurons in the layer.

### Claim 11 (depends on 8)

The critical neuron pruning system of claim 8, wherein the pruning comprises removing the number of critical neurons from the layer and weights associated with the critical neurons from the layer.

### Claim 12 (depends on 8)

The critical neuron pruning system of claim 8, wherein the critical neurons are determined based on features associated with each neuron comprising forward propagation-based features and back propagation-based features.

### Claim 13 (depends on 8)

The critical neuron pruning system of claim 8, wherein the weight pruning is implemented layer-wise.

### Claim 14

A method, comprising:
receiving a normalized feature vector corresponding to each neuron in a layer of a neural network;
calculating a score for each neuron in the layer, wherein the score is based on the normalized feature vector and features collected during training of the neural network; and
determining a set of neurons having a score lower than a threshold, wherein the neurons in the set of neurons are identified as critical neurons.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
receiving a pruning rate parameter.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
determining a number of critical neurons for a layer of the network based on the pruning rate parameter and a total number of neurons in the layer.

### Claim 17 (depends on 14)

The method of claim 14, further comprising:
pruning the critical neurons from the neural network, wherein the pruning generates a pruned neural network with the critical neurons removed.

### Claim 18 (depends on 17)

The method of claim 17, wherein the pruning comprises removing the number of critical neurons from the layer and weights associated with the critical neurons from the layer.

### Claim 19 (depends on 17)

The method of claim 17, wherein the pruning of the critical neurons is implemented layer-wise.

### Claim 20 (depends on 17)

The method of claim 17, wherein the pruning of the critical neurons is implemented globally.