A sequential modeling method based on split-loop neural network

A cyclic neural network and model building technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve problems such as slow RNN speed, improve accuracy, improve training speed, and improve the ability to retain important information Effect

Active Publication Date: 2018-12-25
上海直画科技有限公司
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention can solve the problem of slow speed of traditional RNN

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
  • A sequential modeling method based on split-loop neural network
  • A sequential modeling method based on split-loop neural network
  • A sequential modeling method based on split-loop neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0062] The present invention defines the following technical terms: RNN (Recurrent neural network): cyclic neural network; CNN (Convolutional neural network): convolutional neural network; LSTM (Long-short term memory): long-term short-term memory network; GRU (Gated recurrent unit ): Gated recurrent unit; SRNN (Sliced ​​recurrent neural network): Sliced ​​recurrent neural network.

[0063] Figure 4 It is a schematic diagram of the structure of SRNN, and the present invention is as follows Figure 4 ...

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 provides a method for establishing a sequence model based on a split-loop neural network. The SRNN of the invention can be trained in parallel by improving the overall structure of the RNN, and the speed of the SRNN is greatly improved compared with the traditional RNN. The SRNN of the invention can obtain the high-level information of the sequence, for example, the lowest RNN can get the information of the vocabulary level, the middle RNN can get the information of the sentence level, the top RNN can get the information of the paragraph level, and SRNN limits each RNN to the length of the minimum subsequence, which effectively improves the ability of retaining the important information in the sequence.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a method for establishing a sequence model based on a segmented recurrent neural network. Background technique [0002] With the development of artificial intelligence and computer hardware, the cyclic neural network is widely used in sequence models such as natural language processing and speech recognition because it can extract deep information such as word order in the sequence, making the performance much better than traditional models. Amplitude increased. The structure of the recurrent neural network is as figure 1 As shown, the length of the sequence in the figure is 8, and the x below represents the input at each moment. If it is a natural language processing task, x represents a word or word, and if it is a speech recognition task, x represents a phoneme. A stands for recurrent unit, which can be SimpleRNN, GRU, LSTM, etc. I represents the initial state, usuall...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045
Inventor 于泽平刘功申
Owner 上海直画科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap