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

Brain cognitive process simulation method based on convolutional recurrent neural network

A technology of cyclic neural network and process simulation, applied in the field of intelligent information processing, can solve problems such as ignorance and achieve good interpretability

Pending Publication Date: 2020-10-16
BEIJING AEROSPACE AUTOMATIC CONTROL RES INST
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional artificial neural network structure ignores a large number of biological rules closely related to the realization of brain-like intelligence

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
  • Brain cognitive process simulation method based on convolutional recurrent neural network
  • Brain cognitive process simulation method based on convolutional recurrent neural network
  • Brain cognitive process simulation method based on convolutional recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Below in conjunction with embodiment and attached Figure 1-7 The present invention is described further.

[0054] like figure 1 Shown, be the method flowchart of the present invention, concrete steps are as follows:

[0055] (1) Design an experimental paradigm for EEG signal acquisition under relevant sensory stimulation conditions, and then collect multi-channel EEG signal data based on the experimental paradigm;

[0056] This part takes visual stimulation as an example to introduce the design of EEG signal acquisition experiment paradigm and EEG signal acquisition under the relevant sensory stimulation conditions:

[0057] A total of 2 types of stimuli were designed:

[0058] The image information contains the target object of interest, which is set as the target stimulus;

[0059] The picture information does not contain the target object, which is set as the interference stimulus.

[0060] The specific experimental process is as follows: the subjects sit a...

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 brain cognitive process simulation method based on a convolutional recurrent neural network, and the method comprises the following steps: (1) enabling a testee to carry outthe testing according to a preset experimental paradigm flow, and synchronously collecting the multichannel electroencephalogram signal data of the testee; (2) performing effective component extraction on the acquired original electroencephalogram signal; (3) determining electroencephalogram efficient characteristics under related stimulation; (4) constructing a dual-channel detection model, andobtaining a fusion feature map extracted under the related stimulation; (5) constructing a regional recommendation network and a regression network; (6) taking the constructed dual-channel detection model, the constructed regional recommendation network and the constructed regression network as a brain cognitive model; forming a training data set by the related stimulation in the step (1) and theelectroencephalogram efficient characteristics determined in the step (3), training a brain cognitive model, and approximating the cognitive relationship between related stimulation signals and electroencephalogram signals, so as to simulate the processing capacity of a human body to the related stimulation.

Description

technical field [0001] The invention relates to a brain cognitive process simulation method based on a convolutional cyclic neural network, belonging to the technical field of intelligent information processing. Background technique [0002] Researching human brain-like neural network models and computing methods, and developing brain-inspired brain-like intelligence technologies are key areas in the future era of intelligence and the focus of a new round of technological revolution. Brain-like intelligence technology can be applied to information processing tasks that humans have advantages over computers, such as machine environmental perception, interaction, autonomous decision-making, and intelligent control. The traditional artificial neural network structure ignores a large number of biological rules closely related to the realization of brain-like intelligence. Carrying out research on the mechanism of brain cognition based on neuroelectrophysiology, as well as resea...

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): G06N3/04G06N3/08G06K9/00G06K9/62
CPCG06N3/08G06N3/045G06F2218/08G06F18/253Y02A90/10
Inventor 徐颂王丽娜刘晶晶王清华蒋彭龙
Owner BEIJING AEROSPACE AUTOMATIC CONTROL RES INST