Structural learning of the Boltzmann machine and its application to life cycle management

Shamshul Bahar Yaakob, Junzo Watada, John Fulcher

    Research output: Contribution to journalArticle

    9 Citations (Scopus)

    Abstract

    The objective of this research is to realise structural learning within a Boltzmann machine (BM), which enables the effective solution of problems defined as mixed integer quadratic programming. Simulation results show that computation time is reduced by up to one-fifth compared to conventional BMs. The computational efficiency of the resulting double-layer BM is approximately expressed as the ratio n divided by N, where n is the number of selected units (neurons/nodes) and N is the total number of units. The double-layer BM was applied to efficiently solve a mean-variance problem using mathematical programming with two objectives: the minimisation of risk and the maximisation of expected return. Finally, the effectiveness of our method is illustrated by way of a life cycle management example. The double-layer BM was able to more effectively select results with lower computational overhead. The results also enable us to more easily understand the internal structure of the BM. Using our proposed model, decision makers are able to select the best solution based on their risk preference from the alternative solutions provided by the proposed method.

    Original languageEnglish
    Pages (from-to)2193-2200
    Number of pages8
    JournalNeurocomputing
    Volume74
    Issue number12-13
    DOIs
    Publication statusPublished - 2011 Jun

    Fingerprint

    Life Cycle Stages
    Life cycle
    Mathematical programming
    Quadratic programming
    Computational efficiency
    Neurons
    Learning
    Efficiency
    Research
    Machine Learning

    Keywords

    • Boltzmann machine (BM)
    • Double-layer bM
    • Hopfield network
    • Life cycle management
    • Mixed integer quadratic programming
    • Structural learning

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Science Applications
    • Cognitive Neuroscience

    Cite this

    Structural learning of the Boltzmann machine and its application to life cycle management. / Bahar Yaakob, Shamshul; Watada, Junzo; Fulcher, John.

    In: Neurocomputing, Vol. 74, No. 12-13, 06.2011, p. 2193-2200.

    Research output: Contribution to journalArticle

    Bahar Yaakob, Shamshul ; Watada, Junzo ; Fulcher, John. / Structural learning of the Boltzmann machine and its application to life cycle management. In: Neurocomputing. 2011 ; Vol. 74, No. 12-13. pp. 2193-2200.
    @article{d34ed22efc9946df97bff5c7d058fc74,
    title = "Structural learning of the Boltzmann machine and its application to life cycle management",
    abstract = "The objective of this research is to realise structural learning within a Boltzmann machine (BM), which enables the effective solution of problems defined as mixed integer quadratic programming. Simulation results show that computation time is reduced by up to one-fifth compared to conventional BMs. The computational efficiency of the resulting double-layer BM is approximately expressed as the ratio n divided by N, where n is the number of selected units (neurons/nodes) and N is the total number of units. The double-layer BM was applied to efficiently solve a mean-variance problem using mathematical programming with two objectives: the minimisation of risk and the maximisation of expected return. Finally, the effectiveness of our method is illustrated by way of a life cycle management example. The double-layer BM was able to more effectively select results with lower computational overhead. The results also enable us to more easily understand the internal structure of the BM. Using our proposed model, decision makers are able to select the best solution based on their risk preference from the alternative solutions provided by the proposed method.",
    keywords = "Boltzmann machine (BM), Double-layer bM, Hopfield network, Life cycle management, Mixed integer quadratic programming, Structural learning",
    author = "{Bahar Yaakob}, Shamshul and Junzo Watada and John Fulcher",
    year = "2011",
    month = "6",
    doi = "10.1016/j.neucom.2011.02.018",
    language = "English",
    volume = "74",
    pages = "2193--2200",
    journal = "Neurocomputing",
    issn = "0925-2312",
    publisher = "Elsevier",
    number = "12-13",

    }

    TY - JOUR

    T1 - Structural learning of the Boltzmann machine and its application to life cycle management

    AU - Bahar Yaakob, Shamshul

    AU - Watada, Junzo

    AU - Fulcher, John

    PY - 2011/6

    Y1 - 2011/6

    N2 - The objective of this research is to realise structural learning within a Boltzmann machine (BM), which enables the effective solution of problems defined as mixed integer quadratic programming. Simulation results show that computation time is reduced by up to one-fifth compared to conventional BMs. The computational efficiency of the resulting double-layer BM is approximately expressed as the ratio n divided by N, where n is the number of selected units (neurons/nodes) and N is the total number of units. The double-layer BM was applied to efficiently solve a mean-variance problem using mathematical programming with two objectives: the minimisation of risk and the maximisation of expected return. Finally, the effectiveness of our method is illustrated by way of a life cycle management example. The double-layer BM was able to more effectively select results with lower computational overhead. The results also enable us to more easily understand the internal structure of the BM. Using our proposed model, decision makers are able to select the best solution based on their risk preference from the alternative solutions provided by the proposed method.

    AB - The objective of this research is to realise structural learning within a Boltzmann machine (BM), which enables the effective solution of problems defined as mixed integer quadratic programming. Simulation results show that computation time is reduced by up to one-fifth compared to conventional BMs. The computational efficiency of the resulting double-layer BM is approximately expressed as the ratio n divided by N, where n is the number of selected units (neurons/nodes) and N is the total number of units. The double-layer BM was applied to efficiently solve a mean-variance problem using mathematical programming with two objectives: the minimisation of risk and the maximisation of expected return. Finally, the effectiveness of our method is illustrated by way of a life cycle management example. The double-layer BM was able to more effectively select results with lower computational overhead. The results also enable us to more easily understand the internal structure of the BM. Using our proposed model, decision makers are able to select the best solution based on their risk preference from the alternative solutions provided by the proposed method.

    KW - Boltzmann machine (BM)

    KW - Double-layer bM

    KW - Hopfield network

    KW - Life cycle management

    KW - Mixed integer quadratic programming

    KW - Structural learning

    UR - http://www.scopus.com/inward/record.url?scp=79956083549&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79956083549&partnerID=8YFLogxK

    U2 - 10.1016/j.neucom.2011.02.018

    DO - 10.1016/j.neucom.2011.02.018

    M3 - Article

    AN - SCOPUS:79956083549

    VL - 74

    SP - 2193

    EP - 2200

    JO - Neurocomputing

    JF - Neurocomputing

    SN - 0925-2312

    IS - 12-13

    ER -