# US 2025/0094797 A1 · System and Method for Constructing Neural Networks Equivariant to Arbitrary Matrix Groups Using Group Representations and Equivariant Tensor Fusion

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

- Number: US 2025/0094797 A1
- Document ID: US20250094797A1
- Status: Published application
- Kind: A1
- Application number: 18/590,358
- Filed: 2024-02-28
- Published: 2025-03-20
- Earliest claimed: 2023-09-20
- Assignees: Mitsubishi Electric Research Laboratories, Inc.
- Applicants: Mitsubishi Electric Research Laboratories, Inc.
- Inventors: Suhas Lohit; Sourya Basu; Matthew Brand
- Web page: https://patentgrep.com/patent/US20250094797A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A robust machine learning system is provided for robust machine learning. The robust machine learning system includes a processor, and a memory storing a robust machine learning program and a Group Representation Network (GRepsNet), wherein the robust machine learning program runining on the processor. In this case the processor is configured to receive an input dataset represented by a first group representation via input layers connected to the GrepsNet, pass/transmit the input dataset through the GRepsNet configured to generate an output dataset represented by an output group representation from the input dataset, wherein the output group is equivalent to the first group, and generate the output dataset from output layers connected to the GRepsNet.

## Claims

### Claim 1

A non-transitory computer-readable medium having stored thereon a set of instructions for data transformations, which if performed by one or more processors, cause the one or more processors to at least:
provide an input dataset represented by an input group representation into input layers connected to a Group Representation Network (GRepsNet);
transform the input dataset by using the GRepsNet configured to generate an output dataset represented by an output group representation from the input dataset, wherein the GRepsNet is designed to be equivariant to a predetermined transformation group; and
output the output dataset from output layers connected to the GRepsNet.

### Claim 2 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the GRepsNet is formed by one or more linear neural layers with no point-wise non-linearities or bias terms when the input group representation is first or higher-order tensors, wherein the linear neural layers combine the input group representation with the output group representation linearly which maintains equivariance to the predetermined transformation group.

### Claim 3 (depends on 2)

The non-transitory computer-readable medium of claim 2, wherein the GRepsNet is configured to create additional higher-order group representations.

### Claim 4 (depends on 2)

The non-transitory computer-readable medium of claim 2, wherein the GRepsNet is formed by one or more invariant non-linearities applied to the outputs of linear neural layers, wherein the outputs of the non-linearities are configured to interact with the output of the linear neural layers and maintain the equivariance to a predetermined transformation group, wherein the invariant non-linearities are represented by Euclidean norm.

### Claim 5 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the GRepsNet consists of multiple layers, wherein each of the multiple layers is equivariant to the predetermined transformation group.

### Claim 6 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein when an invariance is required at the output dataset, a pooling invariant layer is additionally arranged at the output layers to pool over group dimensions in the output dataset.

### Claim 7

A data transformation system, comprising:
a memory configured to store a Group Representation Network (GRepsNet) and a set of instructions for data transformations using the GRepsNet; and
a processor coupled to the memory and configured to perform the set of instructions including steps of:
providing an input dataset represented by an input group representation into input layers connected to a Group Representation Network (GRepsNet);
transforming the input dataset by using the GRepsNet configured to generate an output dataset represented by an output group representation from the input dataset, wherein the GRepsNet is designed to be equivariant to a predetermined transformation group; and
outputting the output dataset from output layers connected to the GRepsNet.

### Claim 8 (depends on 7)

The data transformation system of claim 7, wherein the GRepsNet is formed by one or more linear neural layers with no-point wise non-linearities or bias terms when the input group representation is first or higher order tensors, wherein the linear neural layers combine the input group representation with the output group representation linearly.

### Claim 9 (depends on 8)

The data transformation system of claim 8, wherein the GRepsNet is configured to create additional higher-order group representations.

### Claim 10 (depends on 8)

The data transformation system of claim 8, wherein the GRepsNet is formed by one or more invariant non-linearities applied to the outputs of linear neural layers, wherein the outputs of the non-linearities are configured to interact with the output of the linear neural layers and maintain the equivariance to a predetermined transformation group, wherein the invariant non-linearities are represented by Euclidean norm.

### Claim 11 (depends on 7)

The data transformation system of claim 7, wherein the GRepsNet consists of multiple layers, wherein each of the multiple layers is equivariant to the predetermined transformation group.

### Claim 12 (depends on 7)

The data transformation system of claim 7, wherein when an invariance is required at the output dataset, a pooling invariant layer is additionally arranged at the output layers to pool over group dimensions in the output dataset.