# US 2023/0274127 A1 · Method and apparatus for learning concept based few-shot

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

- Number: US 2023/0274127 A1
- Document ID: US20230274127A1
- Status: Published application
- Kind: A1
- Application number: 18/088,428
- Filed: 2022-12-23
- Published: 2023-08-31
- Earliest claimed: 2022-02-25
- Assignees: Electronics and Telecommunications Research Institute
- Applicants: Electronics and Telecommunications Research Institute
- Inventors: Hyun Woo KIM; Jeon Gue PARK; Hwajeon SONG; Jeongmin YANG; Byunghyun YOO; Euisok CHUNG; Ran HAN
- Web page: https://patentgrep.com/patent/US20230274127A1

## CPC

- G06N 3/045: Combinations of networks
- G06V 10/764: using classification, e.g. of video objects
- G06F 18/15: Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
- G06F 18/211: Selection of the most significant subset of features
- G06F 18/213: Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/241: relating to the classification model, e.g. parametric or non-parametric approaches
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/096: Transfer learning
- G06V 10/768: {using context analysis, e.g. recognition aided by known co-occurring patterns}
- G06V 10/82: using neural networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A concept based few-shot learning method is disclosed. The method includes estimating a task embedding corresponding to a task to be executed from support data that is a small amount of learning data; calculating a slot probability of a concept memory necessary for a task based on the task embedding; extracting features of query data that is test data, and of the support data; comparing local features for the extracted features with slots of a concept memory to extract a concept, and generating synthesis features to have maximum similarity to the extracted features through the slots of the concept memory; and calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight.

## Claims

### Claim 1

A concept based few-shot learning method executed by a computer, the concept based few-shot learning method comprising:
estimating a task embedding corresponding to a task to be executed from support data that is a small amount of learning data;
calculating a slot probability of a concept memory necessary for a task based on the task embedding;
extracting features of query data that is test data, and of the support data;
comparing local features for the extracted features with slots of a concept memory to extract a concept, and generating synthesis features to have maximum similarity to the extracted features through the slots of the concept memory; and
calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight.

### Claim 2 (depends on 1)

The concept based few-shot learning method of claim 1, wherein the estimating the task embedding corresponding to the task to be executed from the support data includes:
extracting digitized vector-type task features from the support data; and
estimating the task embedding based on context information of the extracted task features.

### Claim 3 (depends on 2)

The concept based few-shot learning method of claim 2, wherein the extracting the digitized vector-type task features from the support data includes:
extracting task features by inputting the support data to a first neural network module; and
extracting task features including context information by inputting the extracted task features to a second neural network module.

### Claim 4 (depends on 3)

The concept based few-shot learning method of claim 3, wherein the estimating the task embedding based on context information of the extracted task features includes:
estimating the task embedding by connecting the task features including the context information and inputting the task features including the context information to a third neural network module.

### Claim 5 (depends on 4)

The concept based few-shot learning method of claim 4, wherein the first to third neural network modules are learned based on a large amount of already prepared base data.

### Claim 6 (depends on 1)

The concept based few-shot learning method of claim 1, wherein the calculating the slot probability of the concept memory necessary for the task based on the task embedding includes:
calculating a slot probability of the concept memory necessary for that task by applying an attention focusing technique to the concept memory and the task embedding.

### Claim 7 (depends on 6)

The concept base few-shot learning method of claim 6, wherein the calculating the slot probability of the concept memory necessary for the task based on the task embedding includes:
calculating a slot probability of a concept memory necessary for that task by applying a cosine similarity function and a softmax function after applying each of matrices learned from base data to a slot of the concept memory and the task embedding.

### Claim 8 (depends on 6)

The concept base few-shot learning method of claim 6, wherein the calculating the slot probability of the concept memory necessary for the task based on the task embedding includes:
calculating a similarity between the slot of the concept memory and the task embedding based on a cosine similarity function, comparing the similarity with a preset threshold, and calculating slot probability by applying the same weight to a slot of concept memory whose similarity exceeds the threshold as a result of the comparison.

### Claim 9 (depends on 1)

The concept based few-shot learning method of claim 1, wherein the calculating the task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight includes:
calculating a prototype for an l-th category of the support data as an average of the concept of the support data; and
calculating a task execution result in which a distance between the prototype and query data is minimized by applying the slot probability as a weight to a difference between the concept of the query data and the calculated prototype.

### Claim 10 (depends on 1)

The concept based few-shot learning method of claim 1, wherein the calculating the task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight includes:
calculating a prototype for an l-th category of the support data as an average of the synthesis feature of the support data; and
calculating a task execution result in which a distance between the prototype and query data is minimized by applying the slot probability as a weight to a difference between the synthesis feature of the query data and the calculated prototype.

### Claim 11 (depends on 1)

The concept based few-shot learning method of claim 1, further comprising:
batch-sampling tasks from base data, generating an episode constructed with support data and query data in each task, and learning a model parameter by applying few-shot learning to the generated episode.

### Claim 12 (depends on 11)

The concept based few-shot learning method of claim 11, wherein the learning the model parameter includes:
extracting features for the generated episode;
generating a synthesis feature and a concept for the extracted features;
calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability of the concept memory as a weight;
calculating a task loss based on a difference between a correct answer and the task execution result, and calculating a synthesis loss based on a distance between the extracted features and the synthesis feature; and
updating a model parameter such that a total loss obtained by adding the synthesis loss to the task loss is minimized.

### Claim 13

A concept based few-shot learning apparatus comprising:
a concept memory for storing a concept feature extracted through learning from base data;
a task estimation unit for extracting digitized task features from support data, which is a small amount of learning data, and for estimating task embedding based on context information of extracted tasks;
a concept attention focusing unit for calculating a slot probability of a concept memory necessary for a task based on the task embedding;
a feature extraction unit for extracting features of query data that is test data, and of the support data;
a concept extraction and synthesis feature generation unit for comparing a local feature for the extracted features with slots of a concept memory to extract a concept, and for generating a synthesis feature having maximum similarity with the extracted features; and
a task execution unit for calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight.

### Claim 14 (depends on 13)

The concept based few-shot learning apparatus of claim 13, wherein the task extraction unit extracts task features by inputting the support data to a first neural network module, extracts task features including context information by inputting the extracted task features to a second neural network module, and estimates the task embedding by connecting the task features including the context information and inputting the task features including the context information to a third neural network module.

### Claim 15 (depends on 13)

The concept based few-shot learning apparatus of claim 13, wherein the concept attention focusing unit calculates a slot probability of the concept memory necessary for that task by applying an attention focusing technique to the concept memory and the task embedding.

### Claim 16 (depends on 15)

The concept based few-shot learning apparatus of claim 15, wherein the concept attention focusing unit calculates a slot probability of a concept memory necessary for that task by applying a cosine similarity function and a softmax function after applying each of matrices learned from base data to a slot of the concept memory and the task embedding.

### Claim 17 (depends on 16)

The concept based few-shot learning apparatus of claim 16, wherein the concept attention focusing unit calculates a similarity between the slot of the concept memory and the task embedding based on a cosine similarity function, compares the similarity with a preset threshold, and calculates slot probability by applying the same weight to a slot of concept memory whose similarity exceeds the threshold as a result of the comparison.

### Claim 18 (depends on 13)

The concept based few-shot learning apparatus of claim 13, wherein the task execution unit calculates a prototype for an l-th category of the support data as an average of the synthesis feature or concept of the support data, and calculates a task execution result in which a distance between the prototype and query data is minimized by applying the slot probability as a weight to a difference between the synthesis feature or concept of the query data and the calculated prototype.

### Claim 19

A learning method for concept based few-shot learning executed by a computer, the concept based few-shot learning method comprising:
batch-sampling a task from base data, and generating an episode constructed with support data and query data in each sampled task;
extracting features for the generated episode;
generating a synthesis feature and a concept for the extracted features;
calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability of the concept memory as a weight;
calculating a task loss based on a difference between a correct answer and the task execution result, and calculating a synthesis loss based on a distance between the extracted features and the synthesis feature; and
updating a model parameter such that a total loss obtained by adding the synthesis loss to the task loss is minimized.
