Image processing using cellular neural networks based on multi-valued and universal binary neurons

被引：0

作者：

Aizenberg, Igor ^{[1
]}

Aizenberg, Naum ^{[1
]}

Bregin, Taras ^{[1
]}

Butakov, Constantine ^{[1
]}

Farberov, Elya ^{[1
]}

机构：

[1] Neural Networks Technologies Ltd, Bnei-Brak, Israel

来源：

Neural Networks for Signal Processing - Proceedings of the IEEE Workshop | 2000年 / 2卷

关键词：

Binary codes - Boolean algebra - Cellular neural networks - Learning algorithms;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Multi-valued and universal binary neurons (MVN and UBN) are the neural processing elements with complex-valued weights and high functionality. It is possible to implement an arbitrary mapping, described by partially-defined multiple-valued function on the single MVN, and an arbitrary mapping, described by partially-defined or full-defined Boolean function (which can be not threshold) on the single UBN. The fast-converging learning algorithms exist for both types of neurons. Such features of the MVN and UBN may be used to solve different kinds of problems. One of the most successful applications of the MVN and UBN is their use as the basic neurons in the Cellular Neural Networks (CNN) to solve image processing and image analysis problems.

引用

页码：557 / 566

共 50 条

[41] Multi-valued neural networks I: a multi-valued associative memory (vol 33, pg 10189, 2021)
Maximov, Dmitry
Goncharenko, Vladimir I.
Legovich, Yury S.
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (24): : 18087 - 18088
[42] Intelligent Detection of Impulse Noise using Multilayer Neural Network with Multi-Valued Neurons
Aizenberg, Igor
Wallace, Glen
IMAGE PROCESSING: ALGORITHMS AND SYSTEMS X AND PARALLEL PROCESSING FOR IMAGING APPLICATIONS II, 2012, 8295
[43] Implementation of multi-valued logic based on bi-threshold neural networks
Deng, Qiuxiang
Zeng, Zhigang
ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 2, PROCEEDINGS, 2007, 4492 : 575 - +
[44] Image processing using hysteretic cellular neural networks
Matei, RP
ISCAS 2000: IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - PROCEEDINGS, VOL IV: EMERGING TECHNOLOGIES FOR THE 21ST CENTURY, 2000, : 129 - 132
[45] Solving selected classification problems in Bioinformatics using multilayer neural network based on multi-valued neurons (MLMVN)
Aizenberg, Igor
Zurada, Jacek M.
ARTIFICIAL NEURAL NETWORKS - ICANN 2007, PT 1, PROCEEDINGS, 2007, 4668 : 874 - +
[46] Blind optical baseband signals detection using recurrent neural network based on continuous multi-valued neurons
Ruan, X. (ruanxiukai@wzu.edu.cn), 1600, Chinese Optical Society (32):
[47] Introducing quaternion multi-valued neural networks with numerical examples
Greenblatt, Aaron B.
Agaian, Sos S.
INFORMATION SCIENCES, 2018, 423 : 326 - 342
[48] Multi-Valued Quantization Neural Networks toward Hardware Implementation
Aratani, Yoshiya
Jye, Yeoh Yoeng
Suzuki, Akihiro
Shuto, Daisuke
Morie, Takashi
Tamukoh, Hakaru
ICAROB 2017: PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON ARTIFICIAL LIFE AND ROBOTICS, 2017, : P132 - P135
[49] Smoothing algorithms for binary image using cellular neural networks
Yang, Tao
Dianzi Kexue Xuekan/Journal of Electronics, 1996, 18 (01): : 7 - 14
[50] Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm
Igor Aizenberg
Claudio Moraga
Soft Computing, 2007, 11 : 169 - 183

← 1 2 3 4 5 →