Implementation of Kohonen´s self-organising maps on MANTRA I

Author

Ienne, Paolo ; Viredaz, Marc A.

Author_Institution

MANTRA Centre for Neuro-Mimetic Syst., Swiss Federal Inst. of Technol., Lausanne, Switzerland

fYear

1994

fDate

26-28 Sep 1994

Firstpage

273

Lastpage

279

Abstract

This paper presents a computer dedicated to neural algorithms. The computational core of the system is a systolic array of dedicated processing elements (PEs). This accelerator provides the primitives to implement several widely used neural models, including Kohonen´s Self-Organizing Maps (SOMs). This paper concentrates on the problems related to the mapping of the SOM algorithm on the machine. Some modifications to the algorithm, required to parallelize it efficiently, are also proposed. Some aspects of the complexity of programming a systolic system are discussed and the chosen software approach is presented

Keywords

self-organising feature maps; Kohonen self-organising maps; MANTRA I; SIMD machine; accelerator; dedicated processing elements; neural algorithms; programming; systolic array; Artificial neural networks; Control systems; Digital signal processing; Hardware; Neural networks; Self organizing feature maps; Signal processing algorithms; Sun; Systolic arrays; Workstations;

fLanguage

English

Publisher

ieee

Conference_Titel

Microelectronics for Neural Networks and Fuzzy Systems, 1994., Proceedings of the Fourth International Conference on

Conference_Location

Turin

Print_ISBN

0-8186-6710-9

Type

conf

DOI

10.1109/ICMNN.1994.593720

Filename

593720