Reserve pool computing system based on dynamic memristor

A computing system and memristor technology, applied in physical realization, biological neural network models, etc., can solve problems such as limiting the speed of RC systems, and achieve the effects of performance optimization, small size, and low power consumption

Inactive Publication Date: 2021-03-12
TSINGHUA UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This extra read operation will limit the speed of such RC systems

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
  • Reserve pool computing system based on dynamic memristor
  • Reserve pool computing system based on dynamic memristor
  • Reserve pool computing system based on dynamic memristor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] 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, and do not limit the protection scope of the present invention.

[0019] In order to better understand the present invention, an application example of a dynamic memristor-based reserve pool computing system proposed by the present invention will be described in detail below.

[0020] see figure 1 , a dynamic memristor-based reserve pool computing system according to an embodiment of the present invention includes:

[0021] The time-division multiplexing module includes n parallel mask units, each mask unit generates a different mask signal, and uses each mask signal as a carrier to modulate the amplitude of the input signal to obtain...

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 reservoir calculation system based on a dynamic memristor, and the system comprises a time division multiplexing module which comprises a plurality of parallel mask units, andmodulates the amplitude of an input signal according to different mask signals through employing each mask signal as a carrier wave, and obtains a plurality of voltage signals with different amplitudes; a reserve pool module which comprises a plurality of reserve pool units, each reserve pool unit comprises a dynamic memristor and a load resistor which are connected with each other, the dynamic memristors are used for carrying out nonlinear transformation on the voltage signals from the mask units to obtain current signals, and the load resistors are used for converting the current signals into voltage signals and then outputting the voltage signals; and a multiply-add module which adopts a non-volatile memristor array, multiply-add operation is carried out on the plurality of voltage signals from the storage battery module and the conductance values of the non-volatile memristors to obtain a plurality of corresponding current signals, then the current signals are output, and the conductance values of the non-volatile memristors correspond to the weight values output by the storage battery system. The working efficiency of the reserve battery system is improved, and the power consumption is reduced.

Description

technical field [0001] The invention belongs to the technical field of reserve pool computing, in particular to a reserve pool computing system based on a dynamic memristor. Background technique [0002] In recent years, artificial neural networks have developed rapidly and played an important role in many different fields, such as object detection, natural language processing, autonomous driving, etc. Generally, neural networks can be roughly divided into two categories in terms of network structure. One is a feed-forward neural network, where neurons are divided into layers and the signal is only propagated forward. There are many types of feed-forward neural networks, including the well-known convolutional neural networks, which are widely used to process static spatial image signals, such as image recognition and object detection. However, such feed-forward structured networks are not suitable for processing temporal signals. Another type of artificial neural network ...

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): G06N3/063
CPCG06N3/063
Inventor 吴华强仲亚楠高滨钱鹤唐建石
Owner TSINGHUA UNIV
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