Estimating Complexity of Classification Tasks Technology Using Neurocomputers

Author

Budnyk, Ivan ; Chebira, Abdennasser ; Madani, Kurosh

Author_Institution

Paris XII Univ., Lieusaint

fYear

2007

fDate

6-8 Sept. 2007

Firstpage

207

Lastpage

212

Abstract

This paper presents an alternative approach for estimating task complexity. Construction of a self-organizing neural tree structure, following the paradigm "divide and rule", requires knowledge about task complexity. Our aim is to determine complexity indicator function and to hallmark its\´ main properties. Described approach uses IBMcopy zero instruction set computer (ZISC-036reg).

Keywords

instruction sets; pattern classification; self-organising feature maps; tree data structures; IBM zero instruction set computer; classification tasks technology; neurocomputers; self-organizing neural tree structure; task complexity; Computer aided instruction; Computer networks; DNA computing; Databases; Modular construction; Neural networks; Neurons; Prototypes; RNA; Tree data structures; DNA (Deoxyribonucleic acid); IBMÂ© Zero Instruction Set Computer (ZISCÂ®) Neurocomputer; Neural tree modular architecture; RNA (Ribonucleic acid); exon; intron; splice junctions;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2007. IDAACS 2007. 4th IEEE Workshop on

Conference_Location

Dortmund

Print_ISBN

978-1-4244-1347-8

Electronic_ISBN

978-1-4244-1348-5

Type

conf

DOI

10.1109/IDAACS.2007.4488406

Filename

4488406