Unlock instant, AI-driven research and patent intelligence for your innovation.

Seeking large network circuit

A network circuit and neural signal technology, applied in the field of large network circuits, can solve the problems of high cost, complex circuit structure, and large number of consuming devices, and achieve the effects of small chip area, low power consumption, and simple structure

Active Publication Date: 2016-01-20
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional large-scale network has the disadvantages of complex circuit structure, large number of components, and high cost.
This must be a fatal shortcoming for future neural network systems with huge components

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
  • Seeking large network circuit
  • Seeking large network circuit
  • Seeking large network circuit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Such as figure 2 The large network circuit of the present invention shown in the present invention has a nerve signal selection unit, and the output terminals of the nerve signal selection unit are respectively connected with the amplification output unit and the nerve signal strength detection unit, and the output terminals of the nerve signal strength detection unit are connected with the amplification The input terminal of the output unit, the neural signal selection unit has n slave V IN1 to V INn The neural signal input terminal, the amplified output unit has n output terminals V OUT1 to V OUTn .

[0023] The nerve signal selection unit is used to control the connection of each nerve signal input terminal with the nerve signal strength detection unit and the amplification output unit according to the control timing;

[0024] The nerve signal strength detection unit is used to detect and save the maximum nerve signal voltage in all nerve signal input terminals,...

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 large network circuit, which has a nerve signal selection unit, the output end of the nerve signal selection unit is respectively connected to the amplification output unit and the nerve signal strength detection unit, and the output end of the nerve signal strength detection unit is connected to the amplification output The input terminal of the unit, the nerve signal selection unit has at least 2 nerve signal input terminals, and the amplifying output unit has a number of output terminals matching the number of nerve signal input terminals on the nerve signal selection unit. The large-scale network circuit of the present invention realizes multiple inputs of the large-scale network circuit on the basis of low power consumption, simple structure and small occupied chip area.

Description

technical field [0001] The invention relates to the fields of semiconductor integrated circuits and neural networks, in particular to a large-scale network circuit for simulating the lateral inhibition phenomenon in biological nervous systems. Background technique [0002] In the biological nervous system, there is a phenomenon of side inhibition, that is, after a neuron is excited, it will inhibit the neurons next to it. This inhibition phenomenon causes competition between neurons: in the initial stage, each neuron It has the same chance of responding to the same input, but because each neuron has different excitability, the most excited neuron has the strongest inhibition on the adjacent neuron, and finally the output of the neuron with the strongest excitability is 1, while the rest of the neurons elements are suppressed and the output is 0. This process is called the Winner-Take-All process. [0003] Another thing that needs to be mentioned is the Hamming neural netwo...

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): H03K19/20
Inventor 刘洋张晓宸董华胡绍刚吴霜毅于奇
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA