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
- EP ID EP84810
- DOI -
- Views 285
- Downloads 0
A Frequency Multiplier Based on Time Recursive Processing
This paper describes a digital frequency multiplier for a pulse rate. The multiplier is based on the recursive processing of the input and output periods and their time differences. Special emphasis is devoted to the tec...
Assessing the Effects of Length, Slope and Distance between Piles on the Bearing Capacity of a Pile Group under Axial Loading in Granular Soil
Piles are usually made of steel, concrete, reinforced concrete or wood, used to enhance the ground’s bearing capacity in order to enable the construction of deep foundations, also called pile foundations. However, the ex...
Fabrication and Characterization of Organoclay Reinforced Polyester Based Hybrid Nanocomposite Materials
Synthesis and characterization of polyester nanocomposites was conducted in order to fabricate hybrid composite materials of polyester/montmorillonite (MMT). Polyester based polymeric nanocomposite materials were synthes...
Impact of a Single Spoiler on Scouring Depth Status Beneath a River Crossing Inclined Pipeline
Deep river crossing pipelines utilized to carry fluids are often placed upon the sand bed. Placement of pipe on the non-smooth bed would result in the production of some local gaps beneath the pipe. Asymmetric scouring i...
Analysis of Children’s Prosodic Features Using Emotion Based Utterances in Urdu Language
Emotion plays a significant role in identifying the states of a speaker using spoken utterances. Prosodic features add sense in spoken utterances providing speaker emotions. The objective of this research is to analyze t...