Modified Hebbian auto-adaptive impulse neural circuits

N. Nintunze; A. Wu

doi:10.1049/el:19901002

Modified Hebbian auto-adaptive impulse neural circuits

N. Nintunze
, A. Wu

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

1 Citation (Scopus)

Abstract

Artificial neural networks learn by adapting interconnection weights. A generalised weight adaptation expression for associative learning has been implemented using synapse circuits based on floating gate devices. A reinforcement depending on the correlation of a synapse input and a neuronal output is used. The circuits also illustrate the influence of the conditioning stimuli amplitude on the conditioning rate.

© The Institution of Electrical Engineers

Original language	English
Pages (from-to)	1561-1563
Journal	Electronics Letters
Volume	26
Issue number	19
DOIs	https://doi.org/10.1049/el:19901002
Publication status	Published - 13 Sept 1990
Externally published	Yes

Access Output

10.1049/el:19901002

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{b455dfd537f94ff08e68c609d3e6158d,

title = "Modified Hebbian auto-adaptive impulse neural circuits",

abstract = "Artificial neural networks learn by adapting interconnection weights. A generalised weight adaptation expression for associative learning has been implemented using synapse circuits based on floating gate devices. A reinforcement depending on the correlation of a synapse input and a neuronal output is used. The circuits also illustrate the influence of the conditioning stimuli amplitude on the conditioning rate. {\textcopyright} The Institution of Electrical Engineers",

author = "N. Nintunze and A. Wu",

year = "1990",

month = sep,

day = "13",

doi = "10.1049/el:19901002",

language = "English",

volume = "26",

pages = "1561--1563",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley \& Sons",

number = "19",

}

TY - JOUR

T1 - Modified Hebbian auto-adaptive impulse neural circuits

AU - Nintunze, N.

AU - Wu, A.

PY - 1990/9/13

Y1 - 1990/9/13

N2 - Artificial neural networks learn by adapting interconnection weights. A generalised weight adaptation expression for associative learning has been implemented using synapse circuits based on floating gate devices. A reinforcement depending on the correlation of a synapse input and a neuronal output is used. The circuits also illustrate the influence of the conditioning stimuli amplitude on the conditioning rate. © The Institution of Electrical Engineers

AB - Artificial neural networks learn by adapting interconnection weights. A generalised weight adaptation expression for associative learning has been implemented using synapse circuits based on floating gate devices. A reinforcement depending on the correlation of a synapse input and a neuronal output is used. The circuits also illustrate the influence of the conditioning stimuli amplitude on the conditioning rate. © The Institution of Electrical Engineers

UR - https://www.scopus.com/pages/publications/0025490995

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0025490995&origin=recordpage

U2 - 10.1049/el:19901002

DO - 10.1049/el:19901002

M3 - RGC 21 - Publication in refereed journal

SN - 0013-5194

VL - 26

SP - 1561

EP - 1563

JO - Electronics Letters

JF - Electronics Letters

IS - 19

ER -

Modified Hebbian auto-adaptive impulse neural circuits

Abstract

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this