# US 2019/0171949 A1 · Model training system, operating method of model training system and portable electronic device

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

- Number: US 2019/0171949 A1
- Document ID: US20190171949A1
- Status: Published application
- Kind: A1
- Application number: 15/833,197
- Filed: 2017-12-06
- Published: 2019-06-06
- Earliest claimed: 2017-12-04
- Assignees: Institute for Information Industry
- Applicants: Institute for Information Industry
- Inventors: Chen-Kuo CHIANG; Cheng-Yeh CHEN; Yi-Ting CHIANG
- Web page: https://patentgrep.com/patent/US20190171949A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N 3/063: using electronic means
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A model training system, an operating method of the model training system and a portable electronic device are provided. The operating method is implemented by a processor. The model training system includes a first model and at least one second model. The processor receives an inputting data. The processor obtains a model difference between the first model and the second model according to the inputting data. The processor obtains an outputting accuracy of the second model according to the inputting data. The processor updates at least one parameter of the second model according to the outputting accuracy and the model difference.

## Claims

### Claim 1

An operating method of a model training system, wherein the operating method is implemented by a processor, the model training system includes a first model and at least one second model, and the operating method comprises:
receiving, by the processor, an inputting data;
obtaining, by the processor, a first intermediate layer data of the first model and a second intermediate layer data of the second model according to inputting data, wherein a difference between the first intermediate layer data and the second intermediate layer data is a model difference between the first model and the second model;
inputting, by the processor, the inputting data to the second model to obtain an output value, and comparing the output value and a target value to obtain an outputting accuracy of the second model; and
updating, by the processor, at least one parameter of the second model according to the outputting accuracy and the model difference.

### Claim 2 (depends on 1)

The operating method of the model training system according to claim 1, wherein the processor updates the at least one parameter of the second model via a deep learning algorithm.

### Claim 3 (depends on 2)

The operating method of the model training system according to claim 2, wherein the deep learning algorithm includes a Stochastic Gradient Descent (SGD) algorithm and an Adaptive Moment Estimation (ADAM) algorithm.

### Claim 4 (depends on 1)

The operating method of the model training system according to claim 1, further comprising:
updating at least one parameter of the first model according to the model difference via a deep learning algorithm.

### Claim 5 (depends on 4)

The operating method of the model training system according to claim 4, wherein the deep learning algorithm includes a Stochastic Gradient Descent (SGD) algorithm and an Adaptive Moment Estimation (ADAM) algorithm.

### Claim 6 (depends on 1)

The operating method of the model training system according to claim 1, wherein the first intermediate layer data and the second intermediate layer data are adjusted, such that a length of the first intermediate layer data which is adjusted and a length of the second intermediate layer data which is adjusted are identical.

### Claim 7 (depends on 1)

The operating method of the model training system according to claim 1, wherein the number of layers of the first model is larger than the number of layers of the second model.

### Claim 8 (depends on 1)

The operating method of the model training system according to claim 1, wherein the number of the at least one second model is more than one, and the first model corresponds to the second models.

### Claim 9

A model training system, comprising:
a first model;
at least one second model;
an inputting unit used for providing an inputting data; and
a processor used for executing an instruction set, wherein the instruction set includes:
a difference analyzing unit used for obtaining a first intermediate layer data of the first model and a second intermediate layer data of the second model according to the inputting data, wherein a difference between the first intermediate layer data and the second intermediate layer data is a model difference between the first model and the second model;
an accuracy analyzing unit used for inputting the inputting data to the second model to obtain an output value, and comparing the outputting value and a target value to obtain an outputting accuracy of the second model; and
a model modifying unit used for updating at least one parameter of the second model according to the outputting accuracy and the model difference.

### Claim 10 (depends on 9)

The model training system according to claim 9, wherein the model modifying unit updates the at least one parameter of the second model via a deep learning algorithm.

### Claim 11 (depends on 10)

The model training system according to claim 10, wherein the deep learning algorithm includes a Stochastic Gradient Descent (SGD) algorithm and an Adaptive Moment Estimation (ADAM) algorithm.

### Claim 12 (depends on 9)

The model training system according to claim 9, wherein the model modifying unit further updates at least one parameter of the first model according to the model difference via a deep learning algorithm.

### Claim 13 (depends on 12)

The model training system according to claim 12, wherein the deep learning algorithm includes a Stochastic Gradient Descent (SGD) algorithm and an Adaptive Moment Estimation (ADAM) algorithm.

### Claim 14 (depends on 9)

The model training system according to claim 9, wherein the difference analyzing unit further comprises:
a length projector used for adjusting the first intermediate layer data and the second intermediate layer data, such that a length of the first intermediate layer data which is adjusted and a length of the second intermediate layer data which is adjusted are identical.

### Claim 15 (depends on 9)

The model training system according to claim 9, wherein the number of layers of the first model is larger than the number of layers of the second model.

### Claim 16 (depends on 9)

The model training system according to claim 9, wherein the number of the at least one second model is more than one, and the first model corresponds to the second model.

### Claim 17 (depends on 16)

The model training system according to claim 16, wherein the second models and the first model are different.

### Claim 18

A portable electronic device, communicated with a server, wherein the server includes a first model, and the portable electronic device comprises:
an inputting unit used for receiving an inputting data;
a second model; and
a processor used for executing an instruction set, wherein the instruction set includes:
a difference analyzing unit used for obtaining a first intermediate layer data of the first model and a second intermediate layer data of the second model according to the inputting data, wherein a difference between the first intermediate layer data and the second intermediate layer data is a model difference between the first model and the second model;
an accuracy analyzing unit used for inputting the inputting data to the second model to obtain an output value, and comparing the outputting value and a target value to obtain an outputting accuracy of the second model; and
a model modifying unit used for updating at least one parameter of the second model according to the outputting accuracy and the model difference.

### Claim 19 (depends on 18)

The portable electronic device according to claim 18, wherein the model modifying unit updates the at least one parameter of the second model via a deep learning algorithm.

### Claim 20 (depends on 19)

The portable electronic device according to claim 19, wherein the deep learning algorithm includes a Stochastic Gradient Descent (SGD) algorithm and an Adaptive Moment Estimation (ADAM) algorithm.

### Claim 21 (depends on 18)

The portable electronic device according to claim 18, wherein the difference analyzing unit further comprises:
a length projector used for adjusting the first intermediate layer data and the second intermediate layer data, such that a length of the first intermediate layer data which is adjusted and a length of the second intermediate layer data which is adjusted are identical.

### Claim 22 (depends on 18)

The portable electronic device according to claim 18, wherein the number of layers of the first model is larger than the number of layers of the second model.

### Claim 23 (depends on 18)

The portable electronic device according to claim 18, wherein the model modifying unit further updates at least one parameter of the first model according to the model difference via a deep learning algorithm.

### Claim 24 (depends on 23)

The portable electronic device according to claim 23, wherein the deep learning algorithm includes a Stochastic Gradient Descent (SGD) algorithm and an Adaptive Moment Estimation (ADAM) algorithm.
