End-to-end model training method and device
A training method and translation model technology, applied in the field of end-to-end model training methods and devices, can solve the problems of reducing model accuracy, single goal, etc.
Active Publication Date: 2021-02-05
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] At present, the traditional end-to-end learning model uses a single goal for optimization during training. What the model can perceive is a good prediction result, but what the model cannot perceive is a bad prediction result, so it is unavoidable. Produce poor results that have a large impact on the overall results, reducing the accuracy of the model
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0023] The following describes the end-to-end model training method and device according to the embodiments of the present application with reference to the accompanying drawings.
[0024] figure 1 is a schematic diagram according to the first embodiment of the present application. Wherein, it should be noted that the execution subject of the end-to-end model train...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The application discloses an end-to-end model training method and device, and relates to the technical field of artificial intelligence. The specific implementation plan is: obtain training data, the training data includes: multiple training samples; the training samples include: the original sequence, the target sequence and the corresponding label list; the label list includes: the important labels in the target sequence and the corresponding avoid labels; avoid The label is an irrelevant label corresponding to an important label; the preset end-to-end model is used to train the preset end-to-end model until the value of the preset optimization objective function is less than the preset threshold, thus, through the training of the end-to-end learning model Improve the data and optimize the objective function, and combine the improved training data and optimize the objective function to train the end-to-end learning model, so that the trained end-to-end model can avoid poor results that have a great impact on the overall result , which improves the accuracy of the model.
Description
technical field [0001] The present application relates to the technical field of data processing, specifically to the technical field of artificial intelligence, and in particular to an end-to-end model training method and device. Background technique [0002] At present, the traditional end-to-end learning model uses a single goal for optimization during training. What the model can perceive is a good prediction result, but what the model cannot perceive is a bad prediction result, so it is unavoidable. Produces poor results that have a large impact on the overall results, reducing the accuracy of the model. Contents of the invention [0003] The present application proposes an end-to-end model training method and device, by using training data to train the preset end-to-end model until the value of the preset optimization objective function is less than the preset threshold, thus, through the peer-to-peer The training data of the end-to-end learning model and the optimi...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06N20/00
CPCG06N20/00G06F40/117G06F18/2113G06F18/2321G06F18/2148G06F18/2115
Inventor 熊皓何中军李芝吴华王海峰
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD