Context-Aware Systems and Applications. Second International Conference, ICCASA 2013, Phu Quoc Island, Vietnam, November 25-26, 2013, Revised Selected Papers

Research Article

A New Fuzzy Associative Memory

Download
3431 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-05939-6_22,
        author={Pham Binh and Nong Hoa and Vu Thai and Quach Truong},
        title={A New Fuzzy Associative Memory},
        proceedings={Context-Aware Systems and Applications. Second International Conference, ICCASA 2013, Phu Quoc Island, Vietnam, November 25-26, 2013, Revised Selected Papers},
        proceedings_a={ICCASA},
        year={2014},
        month={6},
        keywords={Fuzzy associative memory Associative memory Artificial neural network Noise tolerance Pattern recognition},
        doi={10.1007/978-3-319-05939-6_22}
    }
    
  • Pham Binh
    Nong Hoa
    Vu Thai
    Quach Truong
    Year: 2014
    A New Fuzzy Associative Memory
    ICCASA
    Springer
    DOI: 10.1007/978-3-319-05939-6_22
Pham Binh1, Nong Hoa1,*, Vu Thai1, Quach Truong1
  • 1: Thainguyen University of Information Technology and Communication
*Contact email: nongthihoa@gmail.com

Abstract

Fuzzy Associative Memory (FAM) is a neural network that stores associations of patterns. The most important advantage of FAM is recalling stored patterns from noisy inputs (noise tolerance). Some FAMs only show associations or content of pattern separately. Therefore, we propose a model of FAM that shows both associations and content of patterns effectively. In learning process, each pair of pattern is learned by the minimum of input and output pattern. Then, all pairs of pattern are generalized by mean of the learning results of each pair. In recalling process, a new threshold is added to improve noise tolerance. We have conducted experiments in pattern recognition to prove the effectiveness of our FAM. Experiment results show that our model tolerates noise better than previous FAMs in two types of noise.