Method to combine chaos and neural network based on the fixed point theory

D. Zhou, K. Yasuda, R. Yokoyama

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    The dynamics of either associative or hierarchical neural network can boil down to the discovery of fixed point or contraction to the already established fixed point in a discrete dynamical system, and strict mathematical calculations have already proven this point. In other words, the dynamics of all types of neural network can be analyzed and explained by using the fixed point theory in the traditional discrete dynamical system. What is equally important is that the explanation and classification of chaos can also be expressed in terms of its relationship with fixed points. This has provided an important link between chaos and neural network in the traditional discrete dynamical system, namely, the fixed point theory. Based on this idea, this paper proposes a method to combine chaos with neural network using the fixed point theory. With a view to practical application, the paper provides several examples on improving pattern recognition ability by adding chaotic noise in learning machines as well as on improving the ability of optimal solution in the large by creating a new Chaotic Hopfield Neural Network. The approach proposed by this paper is proved user friendly and universally applicable through lab experiments of pattern recognition and solution of the Traveling Salesman Problem on a set of 100 cities.

    Original languageEnglish
    Pages (from-to)645-648
    Number of pages4
    JournalUnknown Journal
    Volume1
    Publication statusPublished - 1997

    Fingerprint

    Chaos theory
    chaos
    Neural networks
    Dynamical systems
    dynamical systems
    Pattern recognition
    Hopfield neural networks
    pattern recognition
    Traveling salesman problem
    traveling salesman problem
    Learning systems
    machine learning
    contraction
    Experiments

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Electronic, Optical and Magnetic Materials

    Cite this

    Zhou, D., Yasuda, K., & Yokoyama, R. (1997). Method to combine chaos and neural network based on the fixed point theory. Unknown Journal, 1, 645-648.

    Method to combine chaos and neural network based on the fixed point theory. / Zhou, D.; Yasuda, K.; Yokoyama, R.

    In: Unknown Journal, Vol. 1, 1997, p. 645-648.

    Research output: Contribution to journalArticle

    Zhou, D, Yasuda, K & Yokoyama, R 1997, 'Method to combine chaos and neural network based on the fixed point theory', Unknown Journal, vol. 1, pp. 645-648.
    Zhou, D. ; Yasuda, K. ; Yokoyama, R. / Method to combine chaos and neural network based on the fixed point theory. In: Unknown Journal. 1997 ; Vol. 1. pp. 645-648.
    @article{5987ce8c7d994db49af641a2aadca8aa,
    title = "Method to combine chaos and neural network based on the fixed point theory",
    abstract = "The dynamics of either associative or hierarchical neural network can boil down to the discovery of fixed point or contraction to the already established fixed point in a discrete dynamical system, and strict mathematical calculations have already proven this point. In other words, the dynamics of all types of neural network can be analyzed and explained by using the fixed point theory in the traditional discrete dynamical system. What is equally important is that the explanation and classification of chaos can also be expressed in terms of its relationship with fixed points. This has provided an important link between chaos and neural network in the traditional discrete dynamical system, namely, the fixed point theory. Based on this idea, this paper proposes a method to combine chaos with neural network using the fixed point theory. With a view to practical application, the paper provides several examples on improving pattern recognition ability by adding chaotic noise in learning machines as well as on improving the ability of optimal solution in the large by creating a new Chaotic Hopfield Neural Network. The approach proposed by this paper is proved user friendly and universally applicable through lab experiments of pattern recognition and solution of the Traveling Salesman Problem on a set of 100 cities.",
    author = "D. Zhou and K. Yasuda and R. Yokoyama",
    year = "1997",
    language = "English",
    volume = "1",
    pages = "645--648",
    journal = "Nuclear Physics A",
    issn = "0375-9474",
    publisher = "Elsevier",

    }

    TY - JOUR

    T1 - Method to combine chaos and neural network based on the fixed point theory

    AU - Zhou, D.

    AU - Yasuda, K.

    AU - Yokoyama, R.

    PY - 1997

    Y1 - 1997

    N2 - The dynamics of either associative or hierarchical neural network can boil down to the discovery of fixed point or contraction to the already established fixed point in a discrete dynamical system, and strict mathematical calculations have already proven this point. In other words, the dynamics of all types of neural network can be analyzed and explained by using the fixed point theory in the traditional discrete dynamical system. What is equally important is that the explanation and classification of chaos can also be expressed in terms of its relationship with fixed points. This has provided an important link between chaos and neural network in the traditional discrete dynamical system, namely, the fixed point theory. Based on this idea, this paper proposes a method to combine chaos with neural network using the fixed point theory. With a view to practical application, the paper provides several examples on improving pattern recognition ability by adding chaotic noise in learning machines as well as on improving the ability of optimal solution in the large by creating a new Chaotic Hopfield Neural Network. The approach proposed by this paper is proved user friendly and universally applicable through lab experiments of pattern recognition and solution of the Traveling Salesman Problem on a set of 100 cities.

    AB - The dynamics of either associative or hierarchical neural network can boil down to the discovery of fixed point or contraction to the already established fixed point in a discrete dynamical system, and strict mathematical calculations have already proven this point. In other words, the dynamics of all types of neural network can be analyzed and explained by using the fixed point theory in the traditional discrete dynamical system. What is equally important is that the explanation and classification of chaos can also be expressed in terms of its relationship with fixed points. This has provided an important link between chaos and neural network in the traditional discrete dynamical system, namely, the fixed point theory. Based on this idea, this paper proposes a method to combine chaos with neural network using the fixed point theory. With a view to practical application, the paper provides several examples on improving pattern recognition ability by adding chaotic noise in learning machines as well as on improving the ability of optimal solution in the large by creating a new Chaotic Hopfield Neural Network. The approach proposed by this paper is proved user friendly and universally applicable through lab experiments of pattern recognition and solution of the Traveling Salesman Problem on a set of 100 cities.

    UR - http://www.scopus.com/inward/record.url?scp=0030661071&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0030661071&partnerID=8YFLogxK

    M3 - Article

    VL - 1

    SP - 645

    EP - 648

    JO - Nuclear Physics A

    JF - Nuclear Physics A

    SN - 0375-9474

    ER -