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

Robot self-organizing-contrastive cognitive development method and system with lifelong learning ability

A learning ability and self-organizing technology, applied in the field of machine learning, can solve problems such as clustering stream data in a non-incremental manner, hindering the combination of SOINN and CFS, and not suitable for SOINN online learning methods, so as to alleviate storage problems and achieve high efficiency. Competitive Learning Strategies, Effects of Improving Clustering Effects

Active Publication Date: 2020-04-24
SHANDONG UNIV
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, the cluster center of CFS is manually selected from the decision graph, which is not suitable for SOINN's online learning method.
The last and most important point that hinders the combination of SOINN and CFS is that CFS is designed for static data and cannot cluster stream data in an incremental manner.

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
  • Robot self-organizing-contrastive cognitive development method and system with lifelong learning ability
  • Robot self-organizing-contrastive cognitive development method and system with lifelong learning ability
  • Robot self-organizing-contrastive cognitive development method and system with lifelong learning ability

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Kolb's Experiential Learning Theory (ELT) describes the human learning process as a continuous cycle. Such as figure 1 As shown, humans first acquire concrete experiences from perception, and then reflect on the learned knowledge and generate abstract concepts. This knowledge can then be used in other experiments or applications. In particular, reflection enables the integration of new experiences into known learning structures. This will promote cognitive development and lifelong learning in humans.

[0038] Based on this, in one or more embodiments, a robot self-organization-reflective cognitive development method with lifelong learning ability is disclosed, including the following process:

[0039] Construct a SORCN cognitive development model based on a single-layer incremental self-organizing neural network; the SORCN is initially an empty network, and gradually develops nodes during the learning period with the input of stream data;

[0040] When the input dat...

Embodiment 2

[0113] In one or more embodiments, a robot self-organization-reflective cognitive development system with lifelong learning capability is disclosed, including:

[0114] A device for constructing a cognitive development model of SORCN based on a single-layer incremental self-organizing neural network; the SORCN starts out as an empty network, and gradually develops nodes during the learning period with the input of stream data;

[0115] means for identifying matching nodes and outputting the corresponding category when the input data is a known category of said SORCN;

[0116] And when the input data is the unknown category of the SORCN, create a new node to learn this knowledge; at the same time, record the new node in a buffer; when the buffer is full, the SORCN proceeds On one reflection, a clustering algorithm is performed, and the resulting clustering results are used to update the SORCN means.

[0117] Those skilled in the art should understand that the specific working ...

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 robot self-organizing-contrastive cognitive development method and system with lifelong learning ability. The method comprises the following steps: constructing an SORCN cognitive development model based on a single-layer incremental self-organizing neural network; when the input data is the known category of the SORCN, identifying a matched node and outputting a corresponding category; when the input data is the unknown category of the SORCN, creating a new node to learn the knowledge; meanwhile, recording the new node in a cache region; and when the buffer area is full, the SORCN carrying out reflection once, executing a clustering algorithm, wherein a generated clustering result is used for updating the SORCN. According to the method, not only can the generalization ability be utilized to relieve the storage problem, but also the efficient competitive learning strategy can be utilized to reduce the calculation amount. In addition, the method can carry out intra-class topology construction in the reflection process, and reliable guidance is provided for adjustment of a node similarity threshold value.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a robot self-organization-reflection cognitive development method and system with lifelong learning ability. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Cognitive development plays an important role in realizing that robots have human-like intelligent behaviors such as perception, attention, reasoning and action. Since a cognitive robot usually needs to work in a complex and changeable environment, it must learn continuous data streams online, convert perceived features into knowledge concepts, remember what it has learned, and be able to call it appropriately according to the situation that arises. And these skills need to be able to be used as ancillary to support higher cognitive ability rather than just for a single task. The...

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): G06N20/00G06N3/08
CPCG06N20/00G06N3/08
Inventor 马昕黄珂李贻斌宋锐荣学文
Owner SHANDONG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com