Special purpose neural net computer system for pattern recognition and application method

A computer system and neural network technology, applied in character and pattern recognition, biological neural network models, computer components, etc., can solve the problem of high misrecognition rate

Active Publication Date: 2007-08-08
INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a special neural network computer system for pattern recognition, practice the bionic pattern recognition theory, improve the sample recognition rate of the pattern recognition system, overcome the high error rate of untrained samples in traditional pattern recognition and the need to add new samples The problem of retraining all samples

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
  • Special purpose neural net computer system for pattern recognition and application method
  • Special purpose neural net computer system for pattern recognition and application method
  • Special purpose neural net computer system for pattern recognition and application method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] The application example of the special neural network computer system for pattern recognition of the present invention is required to perform recognition demonstration on physical models with different angles on the horizontal plane. The collection of samples is to use the microcomputer to observe the collected Bmp files from different directions for screening and sorting to form a training sample set S={S i ′|i=0...j} (where, i is the serial number of the training sample, j is the number of the training sample, S i’ is the i-th training sample). Then, the special neural network computer system for pattern recognition of the present invention performs feature extraction on the samples in the training sample set, and each sample image obtains a 256-dimensional feature vector. Since the observation directions are all horizontal, it can be said that the change of direction has only one variable. Therefore, the distribution of sample points in the feature space is a one-di...

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 a neural net computer system and its method of mode identification single-purpose which comprises: a bus, a storage part to provide data storage space, an arithmetic / logical calculation and control part to do arithmetic / logical calculation, and controls the operation and data exchanging of other parts by bus control system, a neural net hardware which receives data from storage part to do arithmetic / logical calculation through bus according to the order of arithmetic / logical calculation and control part, and stores the results into storage part, an environment interface part which obtains information by the order of arithmetic / logical calculation and control part or expresses system operation results by voice or other modes.

Description

technical field [0001] The invention belongs to the field of computers, and more specifically relates to a special neural network computer system for pattern recognition. Background technique [0002] The development of pattern recognition represented by Fisher and Vapnik has a history of several decades and has achieved remarkable results. However, these traditional pattern recognition methods only pay attention to the "division" between various sample types, and do not pay attention to the characteristics of the same sample itself. This pattern recognition method based on the idea of ​​"dividing" cannot overcome the problem of large misrecognition rate of untrained samples, and every time a new type of sample is added, all types of samples need to be retrained. [0003] In recent years, academician Wang Shoujue has proposed a new theory of bionic pattern recognition, which fundamentally breaks through the idea of ​​"division" in traditional pattern recognition, and uses t...

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): G06N3/02G06K9/66
Inventor 王守觉李卫军赵顾良孙华
Owner INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
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