Novel neural network model for simulating biological bidirectional cognition capability, and training method

A neural network model and neural network technology, applied in the field of new neural network model and training for simulating biological bidirectional cognitive ability, can solve problems such as poor generalization ability and slow convergence speed

Active Publication Date: 2017-04-12
LIAONING TECHNICAL UNIVERSITY
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above problems, the present invention provides a novel neural network model and training method for simulating biological bidirectional cognitive ability, and establishes a mutual learning neural netw

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
  • Novel neural network model for simulating biological bidirectional cognition capability, and training method
  • Novel neural network model for simulating biological bidirectional cognition capability, and training method
  • Novel neural network model for simulating biological bidirectional cognition capability, and training method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0085] (1) Introduction to numerical experiment methods

[0086] Since each iteration of the mutual learning neural network training method (ML, Mutual Learning) includes two learning processes, positive and negative, the standard positive training method STD-PL (Standard Positive Learning) [1] only includes one positive learning process. Therefore, under the same number of iterations, the learning process and learning time of the mutual learning neural network training method are twice that of the standard forward training method. In order to compare the performance of the mutual learning neural network training method and the standard forward training method comprehensively and fairly, four different training methods are used in the numerical experiment part: Equal Process Mutual Learning EP-ML (Equal Process Mutual Learning), Equal Process Transformation Learning EPT- ML (Equal Process Transformation Mutual Learning), EI-ML (Equal Iteration Mutual Learning) with equal itera...

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 discloses a novel neural network model for simulating biological bidirectional cognition capability, and a training method. The model consists of a positive neural network and a negative neural network. The positive neural network completes the simulation of a positive cognition process from the input to the output, and the negative neural network completes the simulation of a positive cognition process from the output to the input, wherein the two neural network structures are symmetric, and share a weight. The corresponding connection weight matrixes of the positive and negative neural networks are in a transposition relation. According to the invention, a coordinative structure of the positive and negative neural networks which are symmetric in structure and shares the weight is built, thereby achieving the simulation of the biological bidirectional cognition capability. A mode of negative learning process is introduced into a process of a standard BP algorithm, and a novel neural network training method is proposed.

Description

technical field [0001] The invention relates to the field of artificial neural networks, in particular to a novel neural network model and a training method for simulating biological bidirectional cognitive abilities. Background technique [0002] Neural network is an information processing system that simulates the structure and functions of the human brain. It is mainly composed of artificial neurons and network structures. The artificial neurons simulate the information processing process of biological neurons, and the network structure simulates the neurons in the biological nervous system. The connection mode, while the network connection weights and biases are responsible for memorizing the corresponding synaptic connection status. As an active marginal interdisciplinary subject, it is becoming a research hotspot in machine learning, artificial intelligence, cognitive science, neurophysiology, nonlinear dynamics and other related fields. [0003] (1) Neural network mo...

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): G06N3/06G06N3/08
CPCG06N3/061G06N3/084
Inventor 刘威郭旭颖刘尚周璇周定宁李瑞丰郭直清黄敏张宇王江付巍巍张雪董艳荣里莹黄梓洋张立忠鞠兴军黄玉凯李雁飞刘欣徐煦赵玉国张琦
Owner LIAONING TECHNICAL UNIVERSITY
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