Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Neural network model processing method and device and data processing method and device

A neural network model and network model technology, applied in the field of data processing methods and devices, and the processing field of neural network models, can solve the problems of high computational overhead and content storage consumption, increased hardware cost and power consumption, and large computational load of neural network models, etc. question

Pending Publication Date: 2021-09-07
ALIBABA GRP HLDG LTD
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the higher the complexity of the neural network model, the greater the computational overhead and content storage consumption, resulting in a corresponding increase in hardware cost and power consumption
[0003] In view of the large amount of calculation of the neural network model in the related technology, which increases the hardware cost and power consumption, no effective solution has been proposed so far.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network model processing method and device and data processing method and device
  • Neural network model processing method and device and data processing method and device
  • Neural network model processing method and device and data processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] According to an embodiment of the present application, a method for processing a neural network model is also provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, Although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0030] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, a server or a similar computing device. figure 1 A block diagram of a hardware structure of a computer terminal (or mobile device) for realizing a processing method of a neural network model is shown. Such as figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (shown by 102a, 102b, ..., 102n in the figure) processor 102 (the proc...

Embodiment 2

[0095] According to an embodiment of the present application, there is also provided a neural network model processing device for implementing the above neural network model processing method, such as Figure 4 As shown, the apparatus 400 includes: a first training module 402 , an acquisition module 404 and a first processing module 406 .

[0096] Wherein, the first training module 402 is used to use the singular value decomposition algorithm and the norm regularization algorithm to train the neural network model to obtain the pre-training model; the acquisition module 404 is used to obtain the target mask matrix corresponding to the pre-training model, wherein, The dimension of the mask matrix is ​​the same as that of the weight matrix of the pre-training model; the first processing module 406 is used to process the weight matrix of the pre-training model by using the mask matrix to obtain the target model.

[0097] It should be noted here that the above-mentioned first train...

Embodiment 3

[0115] According to an embodiment of the present application, a data processing method is also provided.

[0116] Figure 5 is a flowchart of a data processing method according to an embodiment of the present application. Such as Figure 5 Said, the method includes the following steps:

[0117] Step S502, acquiring the speech signal to be processed.

[0118] The voice signal to be processed in the above steps can be sent by the user and collected by an audio collection device such as a microphone.

[0119] Step S504, using the target model to recognize the speech signal to obtain the recognition result, wherein the target model is obtained by processing the weight matrix of the pre-training model by using the target mask matrix, and the pre-training model is obtained by using the singular value decomposition algorithm and norm regularization It is obtained by training the neural network model with the optimization algorithm, and the dimension of the target mask matrix is ​...

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

No PUM Login to View More

Abstract

The invention discloses a neural network model processing method and device and a data processing method and device. The neural network model processing method comprises the following steps: training a neural network model by using a singular value decomposition algorithm and a norm regularization algorithm to obtain a pre-trained model; obtaining a target mask matrix corresponding to the pre-training model, wherein the dimension of the target mask matrix is the same as the dimension of a weight matrix of the pre-training model; and processing the weight matrix of the pre-training model by using the target mask matrix to obtain a target model. The technical problems that the calculation amount of a neural network model is large, and hardware cost and power consumption are increased in the prior art are solved.

Description

technical field [0001] The present application relates to the field of machine learning, in particular, to a neural network model processing method and device, and a data processing method and device. Background technique [0002] The neural network model is an algorithmic mathematical model that can perform distributed parallel information processing. Depending on the complexity of the model, the purpose of processing information can be achieved by adjusting the interconnection relationship between a large number of internal nodes. However, the higher the complexity of the neural network model, the greater the computational overhead and content storage consumption, resulting in a corresponding increase in hardware cost and power consumption. [0003] Aiming at the problems in related technologies that the neural network model has a large amount of calculation and increases hardware cost and power consumption, no effective solution has been proposed yet. Contents of the in...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/063G06N3/08G06N3/04
CPCG06N3/063G06N3/082G06N3/045
Inventor 涂小兵薛盛可鲁路张伟丰
Owner ALIBABA GRP HLDG LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com