# US 2026/0073662 A1 · Encoder neural networks with power constrained latent representations

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

- Number: US 2026/0073662 A1
- Document ID: US20260073662A1
- Status: Published application
- Kind: A1
- Application number: 19/186,201
- Filed: 2025-04-22
- Published: 2026-03-12
- Earliest claimed: 2024-04-22
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: William R. Mark; Andrey Zhmoginov
- Web page: https://patentgrep.com/patent/US20260073662A1

## CPC

- G06V 10/72: Data preparation, e.g. statistical preprocessing of image or video features
- G06V 10/30: Noise filtering
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/776: Validation; Performance evaluation
- G06V 10/82: using neural networks
- G06V 10/96: Management of image or video recognition tasks
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network to minimize the capacity of an encoded representation of an input observation subject to a per-observation distortion constraint.

## Claims

### Claim 1

A method performed by one or more computers, the method comprising:
receiving an input observation;
processing the input observation using an encoder neural network to generate an encoder output that comprises:
(i) an initial latent vector representing at least a portion of the input observation; and
(ii) a power output that defines a noise power for the initial latent vector;
determining a scaling factor from the power output; and
applying the scaling factor to the initial latent vector to generate a final latent vector representing at least the portion of the input observation and having a constrained signal power.

### Claim 2 (depends on 1)

The method of claim 1, wherein the input observation is an image.

### Claim 3 (depends on 1)

The method of claim 1, wherein the input observation is audio data representing an audio signal.

### Claim 4 (depends on 1)

The method of claim 1, wherein the input observation is a video.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
sampling a noise vector from a noise distribution;
scaling the noise vector using a factor that is defined by the noise power to generate a scaled noise vector; and
adding the scaled noise vector to the final latent vector to generate a noisy latent vector.

### Claim 6 (depends on 5)

The method of claim 5, wherein scaling the noise vector using a factor that is defined by the noise power to generate a scaled noise vector comprises multiplying the noise vector by a square root of the noise power.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
processing a decoder input comprising the noisy latent vector using a decoder neural network to generate a reconstruction of the input observation.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
training the decoder neural network and the encoder neural network jointly on an objective that, for the input observation, minimizes a capacity of the input observation as defined by the noise power subject to a constraint on a per-observation distortion of the reconstruction of the input observation relative to the input observation.

### Claim 9 (depends on 8)

The method of claim 8, wherein:
the encoder output further comprises a Lagrangian output that defines a per-observation Lagrange multiplier for the objective, and
the objective comprises:
a first loss term that represents the capacity and the constraint in terms of the per-observation Lagrange multiplier, and
a second loss term for updating the per-observation Lagrange multiplier.

### Claim 10 (depends on 1)

The method of claim 1, wherein applying the scaling factor to the initial latent vector constrains the final latent vector to have a signal power that is equal to one minus the noise power.

### Claim 11 (depends on 1)

The method of claim 1, wherein determining a scaling factor from the power output comprises:
determining a ratio of signal power to noise power from the power output; and
determining the scaling factor from a signal power of the initial latent vector and the ratio.

### Claim 12 (depends on 11)

The method of claim 11, wherein determining the ratio comprises computing an exponential of the power output.

### Claim 13 (depends on 11)

The method of claim 11, further comprising:
determining the noise power from the ratio.

### Claim 14 (depends on 1)

The method of claim 1, further comprising:
processing an input derived from the final latent vector using a downstream neural network to perform a downstream task.

### Claim 15 (depends on 14)

The method of claim 14, wherein the downstream task is a classification task.

### Claim 16 (depends on 14)

The method of claim 14, wherein the downstream task is a multi-modal task.

### Claim 17 (depends on 14)

The method of claim 14, wherein the input comprises the noisy latent vector.

### Claim 18

A system comprising:
one or more computers; and
one or more storage devices communicatively coupled to the one or more computers, wherein the one or more storage devices store instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
receiving an input observation;
processing the input observation using an encoder neural network to generate an encoder output that comprises:
(i) an initial latent vector representing at least a portion of the input observation; and
(ii) a power output that defines a noise power for the initial latent vector;
determining a scaling factor from the power output; and
applying the scaling factor to the initial latent vector to generate a final latent vector representing at least the portion of the input observation and having a constrained signal power.

### Claim 19

The system of 18, the operations further comprising:
sampling a noise vector from a noise distribution;
scaling the noise vector using a factor that is defined by the noise power to generate a scaled noise vector;
adding the scaled noise vector to the final latent vector to generate a noisy latent vector;
processing a decoder input comprising the noisy latent vector using a decoder neural network to generate a reconstruction of the input observation; and
training the decoder neural network and the encoder neural network jointly on an objective that, for the input observation, minimizes a capacity of the input observation as defined by the noise power subject to a constraint on a per-observation distortion of the reconstruction of the input observation relative to the input observation.

### Claim 20

One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving an input observation;
processing the input observation using an encoder neural network to generate an encoder output that comprises:
(i) an initial latent vector representing at least a portion of the input observation; and
(ii) a power output that defines a noise power for the initial latent vector;
determining a scaling factor from the power output; and
applying the scaling factor to the initial latent vector to generate a final latent vector representing at least the portion of the input observation and having a constrained signal power.
