# US 2023/0410485 A1 · Machine learning device and recording medium

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

- Number: US 2023/0410485 A1
- Document ID: US20230410485A1
- Status: Published application
- Kind: A1
- Application number: 18/203,963
- Filed: 2023-05-31
- Published: 2023-12-21
- Earliest claimed: 2022-06-20
- Assignees: Toyota Jidosha Kabushiki Kaisha
- Applicants: Toyota Jidosha Kabushiki Kaisha
- Inventors: Yoshihisa SHINODA; Shigeki NAKAYAMA; Koji IDE; Tomohiro KANEKO; Hiroshi OYAGI; Masaki ITO; Yuki TAKAHASHI
- Web page: https://patentgrep.com/patent/US20230410485A1

## CPC

- G06V 10/764: using classification, e.g. of video objects
- G06V 10/776: Validation; Performance evaluation
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A machine learning device includes a processor which performs, when performing learning of a model with image data, the learning of the model while excluding the image data of an animal having a feature amount common with a feature amount of a human.

## Claims

### Claim 1

A machine learning device comprising:
a processor, wherein
the processor is configured to perform, when performing learning of a model with image data, the learning of the model while excluding the image data of an animal having a feature amount common with a feature amount of a human.

### Claim 2 (depends on 1)

The machine learning device according to claim 1, wherein
the processor is configured to
determine presence or absence of erroneous recognition in a created model, and
change the feature amount common with the feature amount of the human or changes the image data to be used for the learning, and performs relearning of the model, in a case of determining that there is the erroneous recognition.

### Claim 3 (depends on 1)

The machine learning device according to claim 1, wherein
the feature amount common with the feature amount of the human is determined based on a kind of the animal.

### Claim 4

A non-transitory computer-readable recording medium storing a machine learning program for causing a processor to execute
learning, when learning a model with image data, the model while excluding the image data of an animal having a feature amount common with a feature amount of a human.

### Claim 5 (depends on 4)

The non-transitory computer-readable recording medium storing the machine learning program according to claim 4, the program causing
the processor to execute
determining presence or absence of erroneous recognition in a created model, and
changing the feature amount common with the feature amount of the human or changing the image data to be used for the learning, and performing relearning of the model in a case of determining that there is the erroneous recognition.

### Claim 6 (depends on 4)

The non-transitory computer-readable recording medium storing the machine learning program according to claim 4, wherein
the feature amount common with the feature amount the human is determined based on a kind of the animal.