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

N-tuple or ram based neural network classification system and method

A classification system, n-tuple technology, applied in the field of neural network classification system, can solve problems such as inaction

Inactive Publication Date: 2006-05-17
INTELLIX AS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One problem with the classification scheme of RAM-Net is that it does nothing when trained on a training set where the distribution of samples between the training classes is highly asymmetric.

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
  • N-tuple or ram based neural network classification system and method
  • N-tuple or ram based neural network classification system and method
  • N-tuple or ram based neural network classification system and method

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0156] This example explains an optimization procedure for adjusting criterion Ξ. We consider N C a training set. The class mark c is a value from 1 to N C an integer of . For each class c we define a simple output score function:

[0157] S c ( v a i ( x ‾ ) , c , β ‾ ) = Σ i ∈ Ω β i Θ k ( v a i ( ...

example 2

[0235] This example explains the optimization procedure for adjusting β.

[0236] Again define a simple output score for each class

[0237] S c ( v a i ( x ‾ ) , c , β ‾ ) = Σ i ∈ Ω Θ k c ( v a i ( x ‾ ) , ...

example 3

[0248] This example also explains the optimization procedure for adjusting β, but using the local characteristic function Q L .

[0249] For each category, we now define as many output scores as there are competing categories, namely N C -1 output score:

[0250] S c ( v a i ( x ‾ ) , c , β ‾ ) = Σ i ∈ Ω Θ k c j , c i ...

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 n-tuple or RAM based neural network classification methods and systems and, more particularly, to n-tuple or RAM based classification systems where the decision criteria applied to obtain the output sources and compare these output sources to obtain a classification are determined during a training process. Accordingly, the invention relates to a system and a method of training a computer classification system which can be defined by a network comprising a number of n-tuples or Look Up Tables (LUTs), with each n-tuple or LUT comprising a number of rows corresponding to at least a subset of possible classes and comprising columns being addressed by signals or elements of sampled training input data examples.

Description

technical field [0001] In general, the present invention relates to N-tuple or random access memory based neural network classification systems, and more particularly to such an N-tuple or random access memory based classification system in which Decision criteria for obtaining output scores and comparing these output scores to obtain classification are determined during training. Background technique [0002] The known way of classifying objects or patterns represented by electrical signals or binary codes, more precisely by signal vectors applied to the input of a neural network classification system, is carried out in a so-called learning or training phase. This stage generally involves the configuration of a classification network to achieve the envisaged classification function as efficiently as possible by using one or more sets of signals, called the learning or training set, which are to be classified into one of the categories The affiliation of each of is known. ...

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 Patents(China)
IPC IPC(8): G06N3/08G06F15/80G06K9/64G06K9/62G06N3/04
CPCG06N3/04G06F18/24
Inventor 克里斯琴·林内伯格托马斯·M·乔根森
Owner INTELLIX AS