Model training method and device thereof

Abstract

The invention discloses a model training method and a device thereof, and belongs to the technical field of artificial intelligence. The method can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and intelligent medical treatment. The method comprises the following steps: acquiring first sample input data and corresponding first reference output data as well as second sample input data and corresponding second reference output data, and completing training of a feature extraction network and a first processing network based on the first sample input data and the first reference output data, and completing training of the trained feature extraction network and the second processing network based on the second sample input data and the corresponding second reference output data. By using the method, a plurality of machine learning models with certain processing relevancy can be synchronously trained, so that the accuracy of the machine learning models can be better improved through training under the condition that the number of samples is limited.

Description

technical field

[0001] The present application relates to the technical field of artificial intelligence, in particular to a method and device for model training. Background technique

[0002] With the research and development of machine learning technology, machine learning models have been applied in many fields, and a certain degree of training is required before machine learning models are applied.

[0003] For a machine learning model, the training of the model is usually: calibrate the sample data to obtain the corresponding benchmark output, input the sample data into the model, and obtain the actual output of the model, based on the actual output of the model and the benchmark corresponding to the sample data Output, adjust the parameters in the model, thus, complete the training of the model.

[0004] Before the model is trained, the sample data needs to be calibrated, and the calibration of the sample data requires a lot of manpower and time. This makes the sampl...

Examples

Embodiment Construction

[0065] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0066] The model training method provided in the embodiment of the present application can be applied to the training of the machine learning model. The so-called Machine Learning (ML) is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. Specializes in the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its application pervades all fields of artificial ...

technical field

[0001] The present application relates to the technical field of artificial intelligence, in particular to a method and device for model training. Background technique

[0002] With the research and development of machine learning technology, machine learning models have been applied in many fields, and a certain degree of training is required before machine learning models are applied.

[0003] For a machine learning model, the training of the model is usually: calibrate the sample data to obtain the corresponding benchmark output, input the sample data into the model, and obtain the actual output of the model, based on the actual output of the model and the benchmark corresponding to the sample data Output, adjust the parameters in the model, thus, complete the training of the model.

[0004] Before the model is trained, the sample data needs to be calibrated, and the calibration of the sample data requires a lot of manpower and time. This makes the sampl...

Examples

Embodiment Construction

[0065] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0066] The model training method provided in the embodiment of the present application can be applied to the training of the machine learning model. The so-called Machine Learning (ML) is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. Specializes in the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its application pervades all fields of artificial ...

Images