An analog-current mode local cluster neural net

Author

Sitte, Joaquin ; Korner, Tim ; Ruckert, Ulrich

Author_Institution

Sch. of Comput. Sci., Queensland Univ. of Technol., Brisbane, Qld., Australia

fYear

1997

fDate

9-12 Sep 1997

Firstpage

237

Lastpage

242

Abstract

The local cluster (LC) artificial neural net is a special kind of multilayer perceptron where the sigmoid functions combine in clusters that have a localised response in input space. The proponents of the LC architecture have shown that it is versatile and trains well. They also suggested that the LC nets could be suitable for realisation in analog VLSI. We investigated the feasibility of an analog realisation of LC nets by following through the complete cycle from design to fabrication. We found that the all the required mathematical functions call be realised in current mode bipolar and CMOS circuits. In this paper we discuss the main design issues paying special attention to the alternative training regimes for an LC chip

Keywords

CMOS analogue integrated circuits; analogue processing circuits; bipolar analogue integrated circuits; current-mode logic; integrated circuit design; multilayer perceptrons; neural chips; CMOS circuits; LC architecture; analog VLSI; analog-current mode local cluster neural net; current mode bipolar circuits; localised response; multilayer perceptron; sigmoid functions; Adaptive control; Circuits; Concurrent computing; Costs; Feedforward neural networks; Hardware; Multilayer perceptrons; Neural networks; Space technology; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Technologies and Factory Automation Proceedings, 1997. ETFA '97., 1997 6th International Conference on

Conference_Location

Los Angeles, CA

Print_ISBN

0-7803-4192-9

Type

conf

DOI

10.1109/ETFA.1997.616275

Filename

616275