VHDL-AMS modeling of self-organizing neural systems

Author

Lopez-Alcantud, Jose-Alejandro ; Kazmierski, Tom

Author_Institution

Univ. Politecnica de Cartegena, Spain

Volume

3

fYear

2000

fDate

2000

Firstpage

734

Abstract

This paper presents VHDL-AMS models and simulation results for a complex, self-organizing neural system based on the adaptive resonance theory. Such neural systems exhibit both discrete and continuous dynamic behavior and consist of a large number of analog equations, a digital controller with analog and digital feedback paths resulting in the complexity that would prohibit analysis with conventional mixed-signal simulation tools

Keywords

ART neural nets; circuit CAD; circuit feedback; circuit simulation; integrated circuit modelling; mixed analogue-digital integrated circuits; neural chips; ART2 neural network; CAD tools; VHDL-AMS modeling; adaptive resonance theory; analog equations; analog feedback paths; continuous dynamic behavior; digital controller; digital feedback paths; discrete dynamic behavior; mixed signal ASIC; mixed-signal simulation; self-organizing neural systems; Circuit simulation; Design automation; Digital circuits; Digital control; Equations; Network synthesis; Neural networks; Neurofeedback; Resonance; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on

Conference_Location

Geneva

Print_ISBN

0-7803-5482-6

Type

conf

DOI

10.1109/ISCAS.2000.856165

Filename

856165