Robust Pattern Recognition Using Chaotic Dynamics in Attractor Recurrent Neural Network

被引：0

作者：

Azarpour, M. ^{[1
]}

Seyyedsalehi, S. A. ^{[1
]}

Taherkhani, A. ^{[2
]}

机构：

[1] Amirkabir Univ Technol, Dept Biomed Engn, Tehran, Iran

[2] Islamic Azad Univ, Takestan Branch, Takestan, Iran

来源：

2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010 | 2010年

关键词：

Chaotic neural networks; Attractor Recurrent Neural Network (ARNN); Chaotic nodes; Nonlinear dynamics; Robust pattern recognition; BIFURCATING NEURON; COMPUTATION; MEMORY; NODES;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Strong abilities of brain, in robust and intelligent processing of data are considered in many researches. Furthermore, chaotic behavior is reported both in microscopic scale (neurons) and macroscopic one (brain behavior). Such evidences made us to incorporate chaotic behavior in artificial neural networks to increase their performance in data processing. Based on this fact, a novel chaotic Attractor Recurrent neural network (CARNN) is presented in this paper. CARNN uses chaotic nodes with quasi logistic map as activation function to create various variability around the formed attractors and a Attractor Recurrent Neural Network (ARNN) as supervisor model for evolution of these chaotic nodes to a appropriate findings. Chaotic behavior of neurons made CARNN to search effectively in attractor basins. Therefore, as results show, this model has a better performance in comparison to ARNN and Feedforward Neural Network (FNN) in robust noisy pattern recognition.

引用

页数：6

共 50 条

[1] Recurrent neural network as a linear attractor for pattern association
Seow, MJ
Asari, VK
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (01): : 246 - 250
[2] RECOGNITION AND CATEGORIZATION IN A STRUCTURED NEURAL NETWORK WITH ATTRACTOR DYNAMICS
FASSNACHT, C
ZIPPELIUS, A
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1991, 2 (01) : 63 - 84
[3] Facial Expression Recognition Using Robust Local Directional Strength Pattern Features and Recurrent Neural Network
Rokkones, Anders Skibeli
Uddin, Md Zia
Torresen, Jim
2019 IEEE 9TH INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE-BERLIN), 2019, : 283 - 288
[4] Pattern recognition using asymmetric attractor neural networks
Jin, T
Zhao, H
PHYSICAL REVIEW E, 2005, 72 (06):
[5] Application of chaotic automata to improve the pattern recognition ability of attractor neural networks
De Menezes, MA
Penna, TJP
INTERNATIONAL JOURNAL OF MODERN PHYSICS C, 1998, 9 (03): : 471 - 479
[6] Design of Chaotic Neural Network for Robust Phoneme Recognition
Taherkhani, Aboozar
Seyyedsalehi, Seyyed Ali
Mohammadi, Arash
ISSPIT: 8TH IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2008, : 106 - +
[7] Pattern Recognition Using Chaotic Neural Networks
Tan, Z.
Hepburn, B. S.
Tucker, C.
Ali, M. K.
DISCRETE DYNAMICS IN NATURE AND SOCIETY, 1998, 2 (04)
[8] Pattern Recognition Using a Recurrent Neural Network Inspired on the Olfactory Bulb
Figueira, Lucas Baggio
Roque, Antonio Carlos
NEW CHALLENGES ON BIOINSPIRED APPLICATIONS: 4TH INTERNATIONAL WORK-CONFERENCE ON THE INTERPLAY BETWEEN NATURAL AND ARTIFICIAL COMPUTATION, IWINAC 2011, PART II, 2011, 6687 : 275 - 285
[9] Tracking a moving target using chaotic dynamics in a recurrent neural network model
Li, Yongtao
Nara, Shigetoshi
NEURAL INFORMATION PROCESSING, PART I, 2008, 4984 : 179 - 188
[10] Local community detection as pattern restoration by attractor dynamics of recurrent neural networks
Okamoto, Hiroshi
BIOSYSTEMS, 2016, 146 : 85 - 90

← 1 2 3 4 5 →