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

Apparatus and method for utilizing parameter genome characterizing neural network connections as building block to construct neural network with feedforward and feedback paths

A neural network, spiking neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc.

Pending Publication Date: 2021-02-09
ORBAI TECH INC
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Working with and training a spiking neural network for a specific task is challenging

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
  • Apparatus and method for utilizing parameter genome characterizing neural network connections as building block to construct neural network with feedforward and feedback paths
  • Apparatus and method for utilizing parameter genome characterizing neural network connections as building block to construct neural network with feedforward and feedback paths
  • Apparatus and method for utilizing parameter genome characterizing neural network connections as building block to construct neural network with feedforward and feedback paths

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The invention belongs to the field of artificial neural networks comprising artificial neurons simulated in software or hardware, which integrate input signals and send signals to other neurons via analog connections. There can be thousands of connections from each neuron to other surrounding neurons, where the synapses along each connection modify the signals between neurons, and the synapses are modified by the transmission of signals, learning. The description of all the geometries of these neurons as well as the connectivity of the connections and properties of the synapses is called the connectome, which completely characterizes the neural network. Novel methods for characterizing connectomes with compact parameter genomes and training spiking neural networks with novel feedback architectures are disclosed, using both for efficient genetic algorithms to evolve spiking neural networks for specific purposes. Genetic algorithms rely on biologically inspired operators ...

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

A method of forming a neural network includes specifying layers of neural network neurons. A parameter genome is defined with numerical parameters characterizing connections between neural network neurons in the layers of neural network neurons, where the connections are defined from a neuron in a current layer to neurons in a set of adjacent layers, and where the parameter genome has a unique representation characterized by kilobytes of numerical parameters. Parameter genomes are combined into a connectome characterizing all connections between all neural network neurons in the connectome, where the connectome has in excess of millions of neural network neurons and billions of connections between the neural network neurons.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to U.S. Provisional Patent Application Serial No. 62 / 687,179, filed June 19, 2018, and U.S. Provisional Patent Application Serial No. 62 / 809,297, filed February 22, 2019, each of which is designated The contents of this application are hereby incorporated by reference. technical field [0003] The present invention relates generally to artificial neural networks. More particularly, the present invention relates to processes and tools for constructing neural networks with feedforward and feedback paths using genome sets of parameters characterizing neural network connections as building blocks. Background technique [0004] Existing multilayer, densely connected deep neural networks (deep neural networks) do not closely resemble true biological neural networks. They are just large mathematical functions with a large number of parameters (statically connected weights), adapted to large ...

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): G06N3/00G06N3/02G06N3/06G06N3/10G06N3/12
CPCG06N3/086G06N3/049G06N3/105G06N3/044G06N3/045
Inventor B·L·奥斯特
Owner ORBAI 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