# US 2022/0027742 A1 · Unsupervised learning

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

- Number: US 2022/0027742 A1
- Document ID: US20220027742A1
- Status: Published application
- Kind: A1
- Application number: 17/443,476
- Filed: 2021-07-27
- Published: 2022-01-27
- Earliest claimed: 2020-07-27
- Assignees: Cortica, Ltd.
- Applicants: Cortica Ltd.
- Inventors: Karina ODINAEV
- Web page: https://patentgrep.com/patent/US20220027742A1

## CPC

- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06F 18/23: Clustering techniques
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 10/82: using neural networks
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for an unsupervised training of a neural network, the method may include initializing a neural network that exhibits at least one invariance; performing multiple training iterations until reaching a last training iteration in which a stop condition is fulfilled; wherein each training iteration except the last training iteration comprises: processing a vast number of media units by the neural network to provide media unit signatures; finding that the stop condition is not reached, and changing multiple neural network weights; wherein the stop condition is related to signatures similarities.

## Claims

### Claim 1

A method for an unsupervised training of a neural network, the method comprises:
initializing a neural network that exhibits at least one invariance;
performing multiple training iterations until reaching a last training iteration in which a stop condition is fulfilled;
wherein each training iteration except the last training iteration comprises:
processing a vast number of media units by the neural network to provide media unit signatures;
finding that the stop condition is not reached, and changing multiple neural network weights; wherein the stop condition is related to signatures similarities.

### Claim 2 (depends on 1)

The method according to claim 1 wherein the last training iteration comprises processing the vast number of media units by the neural network to provide media unit signatures and finding that the stop condition is reached.

### Claim 3 (depends on 1)

The method according to claim 1 wherein the signatures similarities are similarities between the media unit signatures.

### Claim 4 (depends on 1)

The method according to claim 1 wherein the each training iteration except the last training iteration comprises:
processing the vast number of media units by the neural network to provide the media unit signatures;
clustering the media unit signatures to provide clusters of media unit signatures;
generating cluster signatures, wherein a cluster signature is indicative of similarities between media unit signatures of the cluster; and
finding that the stop condition is not reached, and changing multiple neural network weights; wherein the signatures similarities are related to one or more similarities between the cluster signatures.

### Claim 5 (depends on 4)

The method according to claim 4 wherein the stop condition is a maximal distance between cluster signatures.

### Claim 6 (depends on 4)

The method according to claim 4 wherein the stop condition is a maximal average distance between cluster signatures.

### Claim 7 (depends on 4)

The method according to claim 4 wherein the stop condition is an average distance between cluster signatures that exceeds a predefined threshold.

### Claim 8 (depends on 1)

The method according to claim 1 wherein the at least one invariance comprises at least one of scale invariance and translation invariance.

### Claim 9

A method for a semi-supervised training of a neural network, the method comprises:
initializing a neural network;
performing multiple training iterations until reaching a last training iteration in which a stop condition is fulfilled;
wherein each training iteration except the last training iteration comprises:
processing a first group of media units and a second group of media units by the neural network to provide first media unit signatures and second media unit signatures; wherein the second group of the media units comprises a vast number of media units; wherein the first group of media units captures an object at different illumination and translation conditions;
finding that the stop condition is not reached, and changing multiple neural network weights; wherein the stop condition is related to a relationship between first media unit signatures of one or more sets of the first media units.

### Claim 10 (depends on 9)

The method according to claim 9 wherein the stop condition is that all first media units signatures are equal to each other.

### Claim 11 (depends on 9)

The method according to claim 9 wherein the stop condition is that all first media units signatures are similar to each other.

### Claim 12 (depends on 9)

The method according to claim 9 wherein the stop condition is indifferent to a relationship between the first media unit signatures.

### Claim 13 (depends on 9)

The method according to claim 9 wherein the at least one invariance comprises at least one of scale invariance and translation invariance.

### Claim 14

A non-transitory computer readable medium that stores instructions for: initializing a neural network that exhibits at least one invariance; performing multiple training iterations until reaching a last training iteration in which a stop condition is fulfilled; wherein each training iteration except the last training iteration comprises: processing a vast number of media units by the neural network to provide media unit signatures; and finding that the stop condition is not reached, and changing multiple neural network weights; wherein the stop condition is related to signatures similarities.
