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

A feedforward sequential memory neural network and its construction method and system

A neural network and construction method technology, applied in biological neural network models, neural architectures, etc., can solve the problem that neural networks cannot guarantee information processing efficiency, and achieve the effect of ensuring information processing efficiency, improving ability, and improving memory ability.

Active Publication Date: 2022-05-17
IFLYTEK CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a feedforward sequence memory neural network and its construction method and system, which solves the problem that the existing neural network cannot guarantee the information processing efficiency under the premise of effectively utilizing the long-term information of the training data, so as to improve user experience Effect

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 feedforward sequential memory neural network and its construction method and system
  • A feedforward sequential memory neural network and its construction method and system
  • A feedforward sequential memory neural network and its construction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] A kind of feed-forward sequence memory neural network comprises a plurality of nodes of at least three layers, the first layer is an input layer, the last layer is an output layer, and other multiple nodes located between the input layer and the output layer form at least one hidden layer, The nodes between layers are fully connected, and also include: each hidden layer contains a memory block, and the hidden layer and the memory block together constitute the FSMN layer of the bidirectional feed-forward sequence memory neural network, where the memory block of the current hidden layer The input of is the output of the current hidden layer, and the output of the memory block of the current hidden layer is an input of the next hidden layer. The memory block is used to store the historical information and future information of the input data of each frame, and the historical information is the current frame The feature sequence of the frame before the input data, the future...

Embodiment 2

[0075] A feedforward sequence memory neural network, as described in Embodiment 1, the difference is that in this embodiment, in order to improve the ability of the neural network to process information data, the bidirectional FSMN stack is replaced by a bidirectional LSFSMN stack, Each bidirectional LSFSMN layer is composed of a bidirectional FSMN layer and an LSTM layer of the same layer, wherein the LSTM layer is used to store historical information, and the bidirectional FSMN layer is used to store future information. The memory capability of the neural network structure for input data is better than that of the neural network structure provided in Embodiment 1.

[0076] A kind of feed-forward sequence memory neural network comprises a plurality of nodes of at least three layers, the first layer is an input layer, the last layer is an output layer, and other multiple nodes located between the input layer and the output layer form at least one hidden layer, The nodes betwee...

Embodiment 3

[0078] A feed-forward sequence memory neural network is as described in the first embodiment, the difference is that in this embodiment, in order to improve the ability of the neural network to process information data, the neural network structure also includes a fully connected stack. The information processing capability of the neural network structure is better than that of the neural network structure provided in Embodiment 1, and the information processing efficiency will not decrease significantly.

[0079] A kind of feed-forward sequence memory neural network comprises a plurality of nodes of at least three layers, the first layer is an input layer, the last layer is an output layer, and other multiple nodes located between the input layer and the output layer form at least one hidden layer, The nodes between layers are fully connected, each hidden layer contains a memory block, and the hidden layer and the memory block together constitute the FSMN layer of the bidirect...

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 feedforward sequence memory neural network and its construction method and system. The feedforward sequence memory neural network includes: a plurality of nodes of at least three layers, the first layer is an input layer, and the last layer is an output layer. Other multiple nodes located between the input layer and the output layer form at least one hidden layer, and each hidden layer includes a memory block, and the hidden layer and the memory block together form a bidirectional feedforward sequence memory neural network FSMN layer, and the memory block uses It is used to store the historical information and future information of the input information of each frame. Since the bidirectional FSMN layer includes a memory block, the historical information and future information of each frame input information can be stored through the memory block, and the long-term information of the training data can be used, and the process does not require bidirectional loop feedback, which can ensure information processing efficiency.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a feedforward sequential memory neural network and its construction method and system. Background technique [0002] Artificial neural network is a kind of model established by simulating the human brain nervous system from the perspective of microstructure and function. It has the ability to simulate part of human image thinking, and its characteristics are mainly nonlinear characteristics, learning ability and adaptability. , is an important way to realize artificial intelligence. It is a network composed of simple information processing units interconnected, which can accept and process information. The information processing of the network is realized by the interaction between units. Handled for connection weights between processing units. In recent years, neural networks have played a vital role in the application systems of human-computer interaction, such as speech...

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 Patents(China)
IPC IPC(8): G06N3/04
CPCG06N3/044
Inventor 张仕良熊世富魏思潘嘉刘聪胡国平胡郁刘庆峰
Owner IFLYTEK CO 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