Bidirectional multiple-valued neural network for pattern recognition and associative recall

被引:0
|
作者
Asari, KV
Eswaran, C
机构
[1] Nanyang Technol Univ, Sch Appl Sci, Singapore 639798, Singapore
[2] Indian Inst Technol, Dept Elect Engn, Madras 600036, Tamil Nadu, India
关键词
neural networks; multiple-valued logic; counter-propagation; self-organization;
D O I
10.1002/1098-1098(2000)11:2<125::AID-IMA3>3.0.CO;2-#
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
A new neural network algorithm based on the counter-propagation network (CPN) architecture, named MVL-CPN, is proposed in this paper for bidirectional mapping and recognition of multiple-valued patterns. The MVL-CPN is capable of performing a mathematical mapping of a set of multiple-valued vector pairs by self-organization. The use of MVL-CPN reduces considerably the number of nodes required for the input layers as well as the number of synaptic weights compared to the binary CPN. The training of the network is stable because all synaptic weights are monotonically nonincreasing. The bidirectional mapping and associative recall features of the MVL-CPN are tested by using various sets of quaternary patterns. It is observed that the MVL-CPN can converge within three or four iterations. The high-speed convergence characteristics of the network can lead to the possibility of using this architecture for real-time applications. An important advantage of the proposed type of neural network is that it can be implemented in VLSI with reduced number of neurons and synaptic weights when compared to a larger binary network needed for the same application. (C) 2000 John Wiley & Sons, Inc.
引用
收藏
页码:125 / 129
页数:5
相关论文
共 50 条
  • [1] NEURAL NETWORK MODEL FOR SELECTIVE ATTENTION IN VISUAL-PATTERN RECOGNITION AND ASSOCIATIVE RECALL
    FUKUSHIMA, K
    [J]. APPLIED OPTICS, 1987, 26 (23) : 4985 - 4992
  • [2] TMLNN: Triple-valued or multiple-valued logic neural network
    Wang, GY
    Shi, HB
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (06): : 1099 - 1117
  • [3] SHADOW CASTING FOR MULTIPLE-VALUED ASSOCIATIVE LOGIC
    ARRATHOON, R
    KOZAITIS, S
    [J]. OPTICAL ENGINEERING, 1986, 25 (01) : 29 - 37
  • [4] Multiple-Valued Artificial Neural Networks
    Makarenko, Alexander
    [J]. 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [5] Real-valued pattern recall by associative memory
    Sossa, H
    Barrón, R
    Oropeza, JL
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE - IBERAMIA 2004, 2004, 3315 : 646 - 655
  • [6] An associative memory neural network to recall nearest pattern from input
    Yamada, I
    Iino, S
    Sakaniwa, K
    [J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1999, E82A (12): : 2811 - 2817
  • [7] Associative Memories Based on Multiple-Valued Sparse Clustered Networks
    Jarollahi, Hooman
    Onizawa, Naoya
    Hanyu, Takahiro
    Gross, Warren J.
    [J]. 2014 IEEE 44TH INTERNATIONAL SYMPOSIUM ON MULTIPLE-VALUED LOGIC (ISMVL 2014), 2014, : 208 - 213
  • [8] Multi-Valued Neural Network Trained by Differential Evolution for Synthesizing Multiple-Valued Functions
    Chen, Huiqin
    Li, Sheng
    Shi, Qian
    Shen, Dongmei
    Gao, Shangce
    [J]. 2015 2ND INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND CONTROL ENGINEERING ICISCE 2015, 2015, : 332 - 335
  • [9] Photonic implementation of Hopfield neural network for associative pattern recognition
    Munshi, S
    Bhattacharyya, S
    Datta, AK
    [J]. PHOTONICS 2000: INTERNATIONAL CONFERENCE ON FIBER OPTICS AND PHOTONICS, 2001, 4417 : 558 - 562
  • [10] Neural networks: Binary monotonic and multiple-valued
    Zurada, JM
    [J]. 30TH IEEE INTERNATIONAL SYMPOSIUM ON MULTIPLE-VALUED LOGIC, PROCEEDINGS, 2000, : 67 - 74