Current-mode implementation of processing modules in ART-based neural networks

Jose-Alejandro Lopez-Alcantud; Hans Hauer; Jose-Angel Diaz-Madrid; Ramon Ruiz-Merino

doi:10.1117/12.499188

18 April 2003 Current-mode implementation of processing modules in ART-based neural networks

Jose-Alejandro Lopez-Alcantud, Hans Hauer, Jose-Angel Diaz-Madrid, Ramon Ruiz-Merino

Proceedings Volume 5119, Bioengineered and Bioinspired Systems; (2003) https://doi.org/10.1117/12.499188
Event: Microtechnologies for the New Millennium 2003, 2003, Maspalomas, Gran Canaria, Canary Islands, Spain

Abstract

This paper describes implementation of neural network processing layers using basic current-mode operating modules. The research work has been focused on the implementation of neural networks based on the Adaptive Resonance Theory, developed by S. Grossberg and G.A. Carpenter. The ART-based neural network whose operating modules have been choosen for development is the one called MART, proposed by F. Delgado, because of its complex architecture, auto--adaptive self-learning process, able to discard unmeaningful cathegories. Our presentation starts introducing the behaviour of MART with an analysis of its structure. The development described by this research work is focused on the monochannel block included in the main signal processing part of the MART neural network. The description of the computing algorithm of the layers inside a monochannel block are also provided in order to show what operational current-mode modules are needed (multiplier, divider, square-rooter, adder, substractor, absolute value, maximum and minimum evaluator...). Descriptions at schematic and layout levels of all the processing layers are given. All of them have been designed using AMS 0.35 micron technology with a supply voltage of 3.3 volts. The modules are designed to deal with input currents in the range of 20 to 50 microamps, showing a lineal behaviour and an output error of less than 10%, which is good enough for neural signal processing systems. The maximum frecuency of operation is around 200 kHz. Simulation results are included to show that the operation performed by the hardware designed matches the behaviour described by the MART neural network. For testing purposes we show the design of a monochannel block hardware implementation restricted to five inputs and three cathegories.

Citation Download Citation

Jose-Alejandro Lopez-Alcantud, Hans Hauer, Jose-Angel Diaz-Madrid, and Ramon Ruiz-Merino "Current-mode implementation of processing modules in ART-based neural networks", Proc. SPIE 5119, Bioengineered and Bioinspired Systems, (18 April 2003); https://doi.org/10.1117/12.499188

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
11 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Information operations

Mirrors

Phase modulation

Signal processing

Binary data

Computing systems

Show All Keywords

Keywords/Phrases

Search In:

Publication Years