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

Method for eliminating data copy, neural network processor and electronic product

A technique of neural network and pulse neural network, which is applied in a method of eliminating data duplication, in the field of neural network processors and electronic products, and can solve problems such as waste of storage space

Active Publication Date: 2021-09-17
HENGDU SYNSENSE TECH CO LTD +1
View PDF16 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There is a potential waste of storage space here

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
  • Method for eliminating data copy, neural network processor and electronic product
  • Method for eliminating data copy, neural network processor and electronic product
  • Method for eliminating data copy, neural network processor and electronic product

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067]Unless otherwise specified, the neuron in the present invention refers to hardware that simulates the working principle of biological neurons at the chip level, such as circuits; and at the algorithm level, it refers to the biological neuron model simulated by software. The pulse referred to in the present invention refers to the spike in the quasi-spiritual field, also known as the spike. When the number of neurons in the neuron cluster is more than one, the connection weights described in the present invention are all weight matrices. In the case of a single neuron, single-valued weights can be regarded as a special case of weight matrices. The operation method of the spiking neural network processor will be described later in conjunction with the hardware structure of the chip. Since various embodiments cannot be exhaustively described, the descriptions in terms of quantity and specifications are only examples, and those skilled in the art can easily think of adaptat...

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 relates to a method for eliminating a data copy, a neural network processor and an electronic product. When neural network hardware is realized, the condition that weight data are the same but belong to connection between different neurons or neuron clusters often occurs, so that enough storage space needs to be reserved when a chip is designed, and therefore, the technical problem of high resource consumption such as power consumption, storage space and even chip area increase of the brain-like chip can be further solved. In order to solve the technical problem, the invention provides a technical means based on source address translation and an alias mechanism. According to the technical scheme based on the technical means, only the neurons corresponding to the alias need to be triggered to register the corresponding activation output when the neurons are activated and output, and the registered corresponding output is output when the neurons corresponding to the alias are activated and output. According to the method, the technical effects of eliminating redundant weight data copies and reducing resource consumption can be realized, and the method is applicable to both an artificial neural network and a spiking neural network.

Description

technical field [0001] The invention relates to a method for eliminating data copies, a neural network processor and an electronic product, in particular to a method for eliminating weight data copies and improving storage space utilization efficiency through an alias (Alias) mechanism, a neural network processor and an electronic product. product. Background technique [0002] In the Spiking Neural Network (SNN) structure, it often occurs that the weight data of two neuron clusters (population, or neurons) are exactly the same. Neurons are circuits that mimic biological neurons, and neuron clusters are collections of circuits that mimic biological neurons. For the spiking neural network processor (also known as pseudo-spiritual processor, brain-like chip) with ultra-low power consumption as its distinctive feature, it is necessary to consider designing a larger storage space, which further means that the power consumption of the chip is increased. . [0003] refer to fi...

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): G06N3/04G06N3/063
CPCG06N3/049G06N3/063
Inventor 乔宁白鑫西克·萨迪克·尤艾尔阿明魏德尔·菲利普
Owner HENGDU SYNSENSE TECH 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