The time dimension of neural network models

Richard Rohwer

    Research output: Contribution to journalArticle

    Abstract

    This review attempts to provide an insightful perspective on the role of time within neural network models and the use of neural networks for problems involving time. The most commonly used neural network models are defined and explained giving mention to important technical issues but avoiding great detail. The relationship between recurrent and feedforward networks is emphasised, along with the distinctions in their practical and theoretical abilities. Some practical examples are discussed to illustrate the major issues concerning the application of neural networks to data with various types of temporal structure, and finally some highlights of current research on the more difficult types of problems are presented.
    Original languageEnglish
    Pages (from-to)36-44
    Number of pages9
    JournalSigart bulletin
    Volume5
    Issue number3
    DOIs
    Publication statusPublished - Jul 1994

    Fingerprint

    Neural networks
    Network model
    Feedforward networks

    Keywords

    • time
    • neural network model
    • recurrent and feedforward networks

    Cite this

    Rohwer, Richard. / The time dimension of neural network models. In: Sigart bulletin. 1994 ; Vol. 5, No. 3. pp. 36-44.
    @article{bc34e97dabf14aa5ad3c5d5074ac4775,
    title = "The time dimension of neural network models",
    abstract = "This review attempts to provide an insightful perspective on the role of time within neural network models and the use of neural networks for problems involving time. The most commonly used neural network models are defined and explained giving mention to important technical issues but avoiding great detail. The relationship between recurrent and feedforward networks is emphasised, along with the distinctions in their practical and theoretical abilities. Some practical examples are discussed to illustrate the major issues concerning the application of neural networks to data with various types of temporal structure, and finally some highlights of current research on the more difficult types of problems are presented.",
    keywords = "time, neural network model, recurrent and feedforward networks",
    author = "Richard Rohwer",
    year = "1994",
    month = "7",
    doi = "10.1145/181911.181917",
    language = "English",
    volume = "5",
    pages = "36--44",
    journal = "Sigart bulletin",
    issn = "0163-5719",
    number = "3",

    }

    The time dimension of neural network models. / Rohwer, Richard.

    In: Sigart bulletin, Vol. 5, No. 3, 07.1994, p. 36-44.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - The time dimension of neural network models

    AU - Rohwer, Richard

    PY - 1994/7

    Y1 - 1994/7

    N2 - This review attempts to provide an insightful perspective on the role of time within neural network models and the use of neural networks for problems involving time. The most commonly used neural network models are defined and explained giving mention to important technical issues but avoiding great detail. The relationship between recurrent and feedforward networks is emphasised, along with the distinctions in their practical and theoretical abilities. Some practical examples are discussed to illustrate the major issues concerning the application of neural networks to data with various types of temporal structure, and finally some highlights of current research on the more difficult types of problems are presented.

    AB - This review attempts to provide an insightful perspective on the role of time within neural network models and the use of neural networks for problems involving time. The most commonly used neural network models are defined and explained giving mention to important technical issues but avoiding great detail. The relationship between recurrent and feedforward networks is emphasised, along with the distinctions in their practical and theoretical abilities. Some practical examples are discussed to illustrate the major issues concerning the application of neural networks to data with various types of temporal structure, and finally some highlights of current research on the more difficult types of problems are presented.

    KW - time

    KW - neural network model

    KW - recurrent and feedforward networks

    UR - https://dl.acm.org/citation.cfm?id=181911.181917

    U2 - 10.1145/181911.181917

    DO - 10.1145/181911.181917

    M3 - Article

    VL - 5

    SP - 36

    EP - 44

    JO - Sigart bulletin

    JF - Sigart bulletin

    SN - 0163-5719

    IS - 3

    ER -