Method and device for training hybrid model

Abstract

The embodiments of the invention relate to a method and a device for training a hybrid model. The hybrid model includes multiple sub-models. The method includes the following steps: determining a first distribution of a first set of data relative to the sub-models in response to the reception of the first set of data; reducing the dimension of the first set of data to determine a second distribution of the first set of data after dimension reduction; updating a third distribution of model parameters used in the sub-models based on the first distribution and the second distribution; determining a fourth distribution of a second set of data relative to the sub-models in response to the reception of the second set of data after the first set of data; reducing the dimension of the second set of data to determine a fifth distribution of the second set of data after dimension reduction; and updating the third distribution based on the fourth distribution and the fifth distribution.

Description

technical field

[0001] Embodiments of the present disclosure relate to the field of machine learning, and more particularly, to methods and apparatus for training hybrid models. Background technique

[0002] With the rapid development of information technology, the scale of data has grown rapidly. Against this background and trend, machine learning has received more and more attention. Cluster analysis is an important basic problem in the field of machine learning. It divides sample points into different clusters, so that sample points with similar characteristics are in the same cluster. In addition, Principal Components Analysis (PCA) is an important technique for simplifying datasets, which is often used to reduce the dimensionality of the data while maintaining the features of the dataset that contribute the most to variance. For data streams with high dimensions (referred to as high-dimensional data streams), Mixture of Probabilistic Principal Components Analyzers (MP...

Examples

Embodiment Construction

[0016] Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0017] As used herein, the term "including" and variations thereof mean open-ended inclusion, ie, "including but not limited to". The term "or" means "and / or" unless specifically stated otherwise. The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment." The term "another embodiment" means "at least one additional embodiment." The terms "first", "se...

technical field

[0001] Embodiments of the present disclosure relate to the field of machine learning, and more particularly, to methods and apparatus for training hybrid models. Background technique

[0002] With the rapid development of information technology, the scale of data has grown rapidly. Against this background and trend, machine learning has received more and more attention. Cluster analysis is an important basic problem in the field of machine learning. It divides sample points into different clusters, so that sample points with similar characteristics are in the same cluster. In addition, Principal Components Analysis (PCA) is an important technique for simplifying datasets, which is often used to reduce the dimensionality of the data while maintaining the features of the dataset that contribute the most to variance. For data streams with high dimensions (referred to as high-dimensional data streams), Mixture of Probabilistic Principal Components Analyzers (MP...

Examples

Embodiment Construction

[0016] Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0017] As used herein, the term "including" and variations thereof mean open-ended inclusion, ie, "including but not limited to". The term "or" means "and / or" unless specifically stated otherwise. The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment." The term "another embodiment" means "at least one additional embodiment." The terms "first", "se...

Images