Recognition of Generalized Patterns by a Differential Polynomial Neural Network

Journal Title: Engineering, Technology & Applied Science Research - Year 2012, Vol 2, Issue 1

Abstract

A lot of problems involve unknown data relations, identification of which can serve as a generalization of their qualities. Relative values of variables are applied in this case, and not the absolute values, which can better make use of data properties in a wide range of the validity. This resembles more to the functionality of the brain, which seems to generalize relations of variables too, than a common pattern classification. Differential polynomial neural network is a new type of neural network designed by the author, which constructs and approximates an unknown differential equation of dependent variables using special type of root multi-parametric polynomials. It creates fractional partial differential terms, describing mutual derivative changes of some variables, likewise the differential equation does. Particular polynomials catch relations of given combinations of input variables. This type of identification is not based on a whole-pattern similarity, but only to the learned hidden generalized relations of variables.

Authors and Affiliations

L. Zjavka

Keywords

Related Articles

On-line Handwriting Signature Verification Based on Using Extreme Points Extraction

This paper presents a method for on-line Handwriting Signature Verification (HSV) using Extreme Points Matching (EPM). EPM does not use direct computation of curve’s curvature thus it does not expect smoothness in the an...

Estimation of Length and Order of Polynomial-based Filter Implemented in the Form of Farrow Structure

Digital polynomial-based interpolation filters implemented using the Farrow structure are used in Digital Signal Processing (DSP) to calculate the signal between its discrete samples. The two basic design parameters for...

Nonuniform C-Band Loop Antenna: A New Approach for Future UWB Applications

Antenna design becomes very difficult at very small wavelengths and a special lab is required to manufacture a small antenna which costs a lot. A new approach is proposed to enhance the bandwidth of the loop antenna whic...

Using Combined One-Time Password for Prevention of Phishing Attacks

Αs technologies and communications develop, more sabotaging attacks occur including phishing attacks which jeopardize users' security and critical information like their passwords and credentials. Several solutions have...

High-level Synthesis Integrated Verification

It is widely known in the engineering community that more than 60% of the IC design project time is spent on verification. For the very complex contemporary chips, this may prove prohibitive for the IC to arrive at the c...

Download PDF file
  • EP ID EP84810
  • DOI -
  • Views 292
  • Downloads 0

How To Cite

L. Zjavka (2012). Recognition of Generalized Patterns by a Differential Polynomial Neural Network. Engineering, Technology & Applied Science Research, 2(1), -. https://europub.co.uk/articles/-A-84810