# US 2025/0165758 A1 · Information processing apparatus and information processing method

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

- Number: US 2025/0165758 A1
- Document ID: US20250165758A1
- Status: Published application
- Kind: A1
- Application number: 18/730,419
- Filed: 2023-02-27
- Published: 2025-05-22
- Earliest claimed: 2022-03-03
- Assignees: Sony Group Corporation
- Applicants: Sony Group Corporation
- Inventors: Hiroyuki Katchi
- Web page: https://patentgrep.com/patent/US20250165758A1

## CPC

- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06F 17/16: Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)}
- G06N 3/02: Neural networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/063: using electronic means
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An information processing apparatus (1) includes a processing unit (11) that generates divided compressed data (dc) by dividing and compressing a coefficient matrix (km) of a neural network, which has dimensions in a filter direction and in other directions and is adjusted to include many zero coefficients, in a divided range designed to be unable to be set freely in the filter direction but to be able to be set freely in the other directions.

## Claims

### Claim 1

An information processing apparatus comprising
a processing unit that generates divided compressed data by dividing and compressing a coefficient matrix of a neural network, which has dimensions in a filter direction and in other directions and is adjusted to include many zero coefficients, in a divided range designed to be unable to be set freely in the filter direction but to be able to be set freely in the other directions.

### Claim 2 (depends on 1)

The information processing apparatus according to claim 1, wherein
the divided compressed data includes non-zero coefficient data in which non-zero coefficients in the coefficient matrix for each of filters are described with raw bits, a sparse matrix in which each of the zero coefficients and the non-zero coefficients in the coefficient matrix for each of the filters is described with one bit, and an address that specifies a position of the non-zero coefficient data.

### Claim 3 (depends on 2)

The information processing apparatus according to claim 2, wherein
the divided range is determined so that a data size of each of the filters in the sparse matrix is equal to or smaller than a data size corresponding to an internal buffer size of an apparatus that restores and uses the divided compressed data.

### Claim 4 (depends on 1)

The information processing apparatus according to claim 1, wherein
the other directions include at least one of a depth direction, a height direction, and a width direction.

### Claim 5 (depends on 1)

The information processing apparatus according to claim 1, wherein
the coefficient matrix includes a coefficient matrix of a convolution layer of the neural network, and
the convolution layer includes at least one of a one-dimensional convolution layer, a two-dimensional convolution layer, a Depthwise convolution layer, and a pointwise convolution layer.

### Claim 6

An information processing apparatus comprising
a processing unit that restores divided compressed data generated by dividing and compressing a coefficient matrix of a neural network, which has dimensions in a filter direction and in other directions and is adjusted to include many zero coefficients, in a divided range designed to be unable to be set freely in the filter direction but to be able to be set freely in the other directions.

### Claim 7 (depends on 6)

The information processing apparatus according to claim 6, wherein
the divided compressed data includes non-zero coefficient data in which non-zero coefficients in the coefficient matrix for each of filters are described with raw bits, a sparse matrix in which each of the zero coefficients and the non-zero coefficients in the coefficient matrix for each of the filters is described with one bit, and an address that specifies a position of the non-zero coefficient data,
the processing unit exclusively allocates data for each of the filters in the sparse matrix to a plurality of decoders,
each of the decoders decodes the non-zero coefficients described in the allocated data, and
the processing unit allocates unallocated data, among the data for each of the filters in the divided compressed data, to the decoder that has decoded all the non-zero coefficients described in the corresponding data among the plurality of decoders.

### Claim 8 (depends on 7)

The information processing apparatus according to claim 7, wherein
the divided range is determined so that a data size of the sparse matrix for each of the filters is equal to or smaller than a data size corresponding to an internal buffer size of the information processing apparatus.

### Claim 9 (depends on 6)

The information processing apparatus according to claim 6, wherein
the other directions include at least one of a depth direction, a height direction, and a width direction.

### Claim 10 (depends on 6)

The information processing apparatus according to claim 6, wherein
the coefficient matrix includes a coefficient matrix of a convolution layer of the neural network, and
the convolution layer includes at least one of a one-dimensional convolution layer, a two-dimensional convolution layer, a Depthwise convolution layer, and a pointwise convolution layer.

### Claim 11

An information processing method comprising
generating divided compressed data by dividing and compressing a coefficient matrix of a neural network, which has dimensions in a filter direction and in other directions and is adjusted to include many zero coefficients, in a divided range designed to be unable to be set freely in the filter direction but to be able to be set freely in the other directions.
