Performance analysis by simulation of floating-gate MOSFETs applied on a bidirectional associative memory architecture
Floating-gate MOSFETs (FGMOSFETs) are devices that can be electrically programmable and have a non-volatile characteristic. This feature can be adopted to configure a basic cell performing as a variable resistance that can be applied in artificial neural networks as a synapse. Based on a simple mode...
Saved in:
Published in | International journal of electronics Vol. 88; no. 2; pp. 159 - 173 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
London
Taylor & Francis Group
01.02.2001
Taylor & Francis |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Floating-gate MOSFETs (FGMOSFETs) are devices that can be electrically programmable and have a non-volatile characteristic. This feature can be adopted to configure a basic cell performing as a variable resistance that can be applied in artificial neural networks as a synapse. Based on a simple model and considering the coupling coefficient of the structure as the gain of a voltage controlled voltage source, the electrical characteristics of a floating-gate MOSFET can be simulated in PSpice and an artificial neural net, such as the bidirectional associative memory (BAM), can be implemented. Therefore a performance analysis of the net may be done with different sets of threshold voltages for the FGMOSFETs configured as a CMOS inverter used as a synapse. The objective is to know pattern pairs in a bidirectional way. The result is a correlation matrix for the BAM as a function of an electrical parameter of the devices, which is directly related to the respective matrix calculated by the matrix dot product, using the method outlined by Kosko. |
---|---|
ISSN: | 0020-7217 1362-3060 |
DOI: | 10.1080/00207210010002069 |