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

Circuit simulating biological neural network based on similar MOS luminescent devices

A neural network and light-emitting device technology, which is applied in the circuit field based on MOS-like light-emitting devices to simulate biological neural networks, can solve the problems of large electrical signal noise and slow speed, and achieve the effects of low crosstalk noise, low cost, and large bandwidth

Inactive Publication Date: 2015-11-11
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Both the biological neural network and the current method of simulating the biological neural network use electrical signals for connection and transmission. However, the transmission of electrical signals has problems such as large noise and slow speed.

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
  • Circuit simulating biological neural network based on similar MOS luminescent devices
  • Circuit simulating biological neural network based on similar MOS luminescent devices
  • Circuit simulating biological neural network based on similar MOS luminescent devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] As mentioned in the background art, a biological neural network is a neural network composed of neurons, axons and synapses, etc., with neurons as the basic unit. The information transmission between neurons is connected through synapses. The axon terminal of the previous neuron acts on the cell body, dendrites or axons of the next neuron to form synapses; a neuron can Thousands of neurons act on axons and receive information from tens of thousands of neurons through dendrites.

[0028] Based on this, the present invention provides a circuit based on a MOS-like light-emitting device to simulate a biological neural network. Taking a circuit based on a PMOS-like light-emitting device to simulate a biological neural network as an example, it includes more than two neural basic units and light Transmission path; the neural basic unit includes a light receiving and converting device and a PMOS-like light-emitting device, and the light receiving and converting device is 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
Login to View More

PUM

No PUM Login to View More

Abstract

A circuit simulating a biological neural network based on similar MOS luminescent devices belongs to the technical field of semiconductor integrated circuits and biological neural networks. The circuit comprises more than two basic neural units and light transmission paths, wherein each basic neural unit comprises neural synapses, of the biological neural network, which are simulated by optical reception and conversion devices which receive optical signals and convert the optical signals into electric signals, and neurons, of the biological neural network, which are simulated by similar MOS luminescent devices which convert electric signals into optical signals, and the light transmission paths simulate axons of the biological neural network. The more than two basic neural units are connected serially or / and in star-shape through the light transmission paths, so as to simulate the biological neural network. The circuit is compatible with the CMOS process, small in area, high in efficiency and convenient for integration, and is of a great importance to research and development of artificial intelligence.

Description

technical field [0001] The invention relates to the technical fields of semiconductor integrated circuits and biological neural networks, in particular to a circuit for simulating biological neural networks based on a MOS-like light-emitting device (that is, a light-emitting device similar to a metal-insulator-semiconductor structure). Background technique [0002] The biological neural network is a neural network composed of neurons, axons, synapses, etc., with neurons as the basic unit. The information transmission between neurons is connected through synapses. The axon terminal of the previous neuron acts on the cell body, dendrites or axons of the next neuron to form a synapse; a neuron can Thousands of neurons act on axons and receive information from tens of thousands of neurons through dendrites. [0003] Both the biological neural network and the current method of simulating the biological neural network use electrical signals for connection and transmission. Howeve...

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
IPC IPC(8): G06N3/067
Inventor 吴霜毅张孟宁宁朱马李亮廖京
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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