Analog VLSI implementation of adaptive neuro-fuzzy inference systems

Author

Sultan, Ahmed ; El-Sayed, Mohamed

Author_Institution

Dept. of Electr. Eng., Alexandria Univ., Egypt

Volume

1

fYear

2000

fDate

2000

Firstpage

558

Abstract

This paper presents an analog VLSI implementation of adaptive neuro-fuzzy inference systems (ANFIS). Stochastic perturbative techniques, which are more VLSI friendly than standard learning techniques such as back-propagation, are used for on-chip learning. The system is tested by the task of predicting the Mackey-Glass chaotic time series. The system is built and simulated with SPICE using CMOS 1.2 μm N-well technological parameters with 5 V supply. The obtained results have shown how on-chip learning is very fast compared to software implemented learning algorithms

Keywords

VLSI; analogue processing circuits; backpropagation; chaos; inference mechanisms; neural chips; time series; 1.2 micron; 5 V; Mackey-Glass chaotic time series; N-well technological parameters; adaptive neuro-fuzzy inference systems; analog VLSI implementation; back-propagation; on-chip learning; stochastic perturbative techniques; Adaptive systems; CMOS technology; Chaos; Computational intelligence; Glass; Neural networks; SPICE; Stochastic processes; System testing; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits and Systems, 2000. ICECS 2000. The 7th IEEE International Conference on

Conference_Location

Jounieh

Print_ISBN

0-7803-6542-9

Type

conf

DOI

10.1109/ICECS.2000.911601

Filename

911601