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

Brain-like neural network with memory and information abstraction functions

A technology of neural network and memory, applied in the field of brain-like neural network

Pending Publication Date: 2021-11-23
NEUROCEAN TECH INC
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing deep learning has not been able to adequately address the above issues

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-like neural network with memory and information abstraction functions
  • Brain-like neural network with memory and information abstraction functions
  • Brain-like neural network with memory and information abstraction functions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0067] See attached figure 1 , the embodiment of the present invention discloses a brain-like neural network with memory and information abstraction functions, including: perception module 1, instance encoding module 2, environment encoding module 3, space encoding module 4, time encoding module 6, motion orientation encoding Module 5, information synthesis and exchange module 7, memory module 8;

[0068] specifically:

[0069] Each module includes a plurali...

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 brain-like neural network with memory and information abstraction functions, the brain-like neural network uses working principles of a hippocampus region and a plurality of peripheral brain regions of a biological brain for reference, and the brain-like neural network comprises a memory module capable of forming scene memory, so that an intelligent agent can efficiently identify an object and carry out space navigation, reasoning and autonomous decision making. Features of each object can be quickly remembered, abstraction and meta-learning can be performed, generalization ability is high, lifelong learning can be performed, a synaptic plasticity process is adopted to adjust weights, partial differential operation is avoided, calculation overhead is lower than that of traditional deep learning, and a basis is provided for design and application of a neural mimicry chip.

Description

technical field [0001] The invention belongs to the field of brain-inspired neural network and artificial intelligence, in particular to a brain-inspired neural network with memory and information abstraction functions. Background technique [0002] Autonomous robots (intelligent agents) need to be able to synthesize their trajectory and multi-modal perception information into contextual memories including time and space sequences to efficiently identify objects (which can be people, objects, environments, spaces) for spatial navigation, Reasoning and autonomous decision-making. It also needs to be able to form an instant memory; it also needs to be able to fine-tune multiple similar but slightly different objects to avoid confusion; and sometimes, it needs to be able to recognize the same object as different results in different contexts. It also needs to be able to extract common information components from multiple similar objects, and perform information abstraction fro...

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): G06N3/063G06N3/04
CPCG06N3/063G06N3/049G06N3/045G06N3/088G06N3/0985G06N3/092
Inventor 任化龙李文强刘阳
Owner NEUROCEAN TECH INC
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