Improving energy consumption of pattern recognition by combining processor-centric and bio-inspired considerations

Yathindu R. Hettiarachchige, Asad I. Khan, Jan Carlo Barca

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    This paper investigates aspects of bio-inspired models that help create more energy efficient methods in pattern recognition. A comparison between a biologically plausible pattern recognition approach and a purely computer based (algorithmic) approach yielded three main findings. Firstly, the occurrence of low-complexity parallel sub-processes within the bio-inspired approach allows higher energy efficiency by relaxing the requirement of having faster processors. Secondly, the bio-inspired approach takes advantage of numerous computationally inexpensive sub-processes that will scale better in massively parallel environments, such as neuromorphic computers, thus providing comparable speed. Finally, it is far more easier to adapt across a range of application domains than its algorithmic counterpart.

    LanguageEnglish
    Pages54-63
    Number of pages10
    JournalBiologically Inspired Cognitive Architectures
    Volume23
    DOIs
    Publication statusPublished - 1 Jan 2018

    Keywords

    • Bio-inspired
    • Distributed pattern recognition
    • Parallelism
    • Strong AI

    Cite this

    @article{f40c6879798a4021b90216f6738e539b,
    title = "Improving energy consumption of pattern recognition by combining processor-centric and bio-inspired considerations",
    abstract = "This paper investigates aspects of bio-inspired models that help create more energy efficient methods in pattern recognition. A comparison between a biologically plausible pattern recognition approach and a purely computer based (algorithmic) approach yielded three main findings. Firstly, the occurrence of low-complexity parallel sub-processes within the bio-inspired approach allows higher energy efficiency by relaxing the requirement of having faster processors. Secondly, the bio-inspired approach takes advantage of numerous computationally inexpensive sub-processes that will scale better in massively parallel environments, such as neuromorphic computers, thus providing comparable speed. Finally, it is far more easier to adapt across a range of application domains than its algorithmic counterpart.",
    keywords = "Bio-inspired, Distributed pattern recognition, Parallelism, Strong AI",
    author = "Hettiarachchige, {Yathindu R.} and Khan, {Asad I.} and Barca, {Jan Carlo}",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.1016/j.bica.2018.01.004",
    language = "English",
    volume = "23",
    pages = "54--63",
    journal = "Biologically Inspired Cognitive Architectures",
    issn = "2212-683X",
    publisher = "Elsevier",

    }

    Improving energy consumption of pattern recognition by combining processor-centric and bio-inspired considerations. / Hettiarachchige, Yathindu R.; Khan, Asad I.; Barca, Jan Carlo.

    In: Biologically Inspired Cognitive Architectures, Vol. 23, 01.01.2018, p. 54-63.

    Research output: Contribution to journalArticleResearchpeer-review

    TY - JOUR

    T1 - Improving energy consumption of pattern recognition by combining processor-centric and bio-inspired considerations

    AU - Hettiarachchige, Yathindu R.

    AU - Khan, Asad I.

    AU - Barca, Jan Carlo

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - This paper investigates aspects of bio-inspired models that help create more energy efficient methods in pattern recognition. A comparison between a biologically plausible pattern recognition approach and a purely computer based (algorithmic) approach yielded three main findings. Firstly, the occurrence of low-complexity parallel sub-processes within the bio-inspired approach allows higher energy efficiency by relaxing the requirement of having faster processors. Secondly, the bio-inspired approach takes advantage of numerous computationally inexpensive sub-processes that will scale better in massively parallel environments, such as neuromorphic computers, thus providing comparable speed. Finally, it is far more easier to adapt across a range of application domains than its algorithmic counterpart.

    AB - This paper investigates aspects of bio-inspired models that help create more energy efficient methods in pattern recognition. A comparison between a biologically plausible pattern recognition approach and a purely computer based (algorithmic) approach yielded three main findings. Firstly, the occurrence of low-complexity parallel sub-processes within the bio-inspired approach allows higher energy efficiency by relaxing the requirement of having faster processors. Secondly, the bio-inspired approach takes advantage of numerous computationally inexpensive sub-processes that will scale better in massively parallel environments, such as neuromorphic computers, thus providing comparable speed. Finally, it is far more easier to adapt across a range of application domains than its algorithmic counterpart.

    KW - Bio-inspired

    KW - Distributed pattern recognition

    KW - Parallelism

    KW - Strong AI

    UR - http://www.scopus.com/inward/record.url?scp=85041354507&partnerID=8YFLogxK

    U2 - 10.1016/j.bica.2018.01.004

    DO - 10.1016/j.bica.2018.01.004

    M3 - Article

    VL - 23

    SP - 54

    EP - 63

    JO - Biologically Inspired Cognitive Architectures

    T2 - Biologically Inspired Cognitive Architectures

    JF - Biologically Inspired Cognitive Architectures

    SN - 2212-683X

    ER -