MULTIPLE LAYER DISCRETE-TIME CELLULAR NEURAL NETWORKS USING TIME-VARIANT TEMPLATES

被引：31

作者：

HARRER, H

机构：

[1] Institute for Network Theory and Circuit Design, Technical University Munich, D-8000

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING | 1993年 / 40卷 / 03期

关键词：

D O I：

10.1109/82.222818

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper provides a more generalized architecture for DTCNN's as originally defined in [1]. It allows multiple layers of different architecture, which can be combined in several interconnection modes. Three elementary building blocks are introduced. Another important extension is the use of time-variant templates. They enable the definition of cyclic templates, where the coefficients are changed every iteration step and a set of templates is applied periodically. The definition of convergence has been adopted for this network structure and important classes of templates are proved to be convergent. Examples are given for the following image processing tasks: Rectangular hull extraction, skeletonization, and halftoning.

引用

页码：191 / 199

页数：9

共 17 条

[1]

BARTFAI G, 1989, 2489 HUNG AC SCI REP

[2] CELLULAR NEURAL NETWORKS - THEORY [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272

[3]

CHUA LO, 1990, ERL UCBERLM90113 U C

[4]

CHUA LO, 1991, ERL UCBERLM9131 U CA

[5]

CROUNSE KR, 1991, ERL UCBERLM91106 U C

[6]

GALIAS Z, 1992, 2ND P IEEE INT WORKS, P23

[7] AN ANALOG IMPLEMENTATION OF DISCRETE-TIME CELLULAR NEURAL NETWORKS [J].

HARRER, H ;

NOSSEK, JA ;

STELZL, R .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (03) :466-476

[8]

HARRER H, 1991, NOV P INT JOINT C NE, P717

[9]

HARRER H, IN PRESS INT J CIRCU

[10]

HARRER H, IN PRESS INT J CIRC

← 1 2 →