Neural network information conversion method and system

A technology of information conversion and hybrid neural network, applied in the direction of biological neural network model, neural architecture, physical realization, etc., can solve the problems of incompatibility, artificial neural network and pulse neural network information, etc., and achieve high conversion efficiency and implementation mode simple and reliable effect

Active Publication Date: 2021-07-09
LYNXI TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in traditional neuromorphic systems, there are mainly two forms of neural networks, one is spiking neural network and the other is artificial neural network. The two have different expressions for the same input information, resulting in artificial neural network and spiking Neural networks are not compatible due to the different information they process

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 information conversion method and system
  • Neural network information conversion method and system
  • Neural network information conversion method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0120] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0121] figure 1 It is a schematic flow chart of the neural network information conversion method of an embodiment, such as figure 1 The shown neural network information conversion methods include:

[0122] Step S1, receiving neuron input information from a previous neuron, including receiving artificial neuron input information from a previous artificial neuron, or receiving spike neuron input information from a previous spike neuron.

[0123] Specifically, in the neural network information conversion method provided in this embodiment, by identifying the input signals of different neural network...

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 present invention relates to a neural network information conversion method and system. The method includes: receiving neuron input information input by a previous neuron, including receiving artificial neuron input information input by a previous artificial neuron, or receiving a previous pulse The input information of the pulse neuron input by the neuron; according to the input information of the artificial neuron input by the previous artificial neuron, the input information of the artificial neuron is converted into a pulse neuron by a preset artificial information conversion algorithm Convert information; or convert the input information of the pulse neuron into artificial neuron conversion information through a preset pulse information conversion algorithm according to the input information of the pulse neuron; output the conversion information of the pulse neuron or the artificial neuron Neurons transform information. The invention realizes the mode of simultaneously compatible with two different neuron information in one neural network, and improves the information processing capability of the neural network.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a neural network information conversion method and system. Background technique [0002] Most of today's artificial neural network research is still implemented in von Neumann computer software and high-performance GPGPU (General Purpose Graphic Processing Units) platform. The hardware overhead, energy consumption and information of the whole process The processing speed is not optimistic. For this reason, the field of neuromorphic computing has developed rapidly in recent years, that is, using hardware circuits to directly construct neural networks to simulate the functions of the brain, trying to achieve a computing platform that is massively parallel, low-energy, and capable of supporting complex pattern learning. [0003] However, in the traditional neuromorphic system, there are two main forms of neural network, one is spiking neural network and the other is artific...

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): G06N3/04G06N3/063
CPCG06N3/04G06N3/063
Inventor 裴京吴臻志施路平邓磊
Owner LYNXI TECH CO LTD
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