Optimization of output spike train encoding for a spiking neuron based on its spatiotemporal input pattern

T.Martin McGinnity, Georgina Cosma, Aboozar Takerkhani

    Research output: Contribution to journalArticle

    Abstract

    A common learning task for a spiking neuron is to map a spatiotemporal input pattern to a target output spike train. There is no prescribed method for selection of the target output spike train. However, the precise spiking pattern of the target output spike train (output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target output spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial sub-optimal output encoding during different learning epochs to find the optimal output encoding. A time varying value of a local event called a spike trace is used to calculate the amount of a required adjustment. The Remote Supervised Method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized output encoding (optimized desired spikes). Experimental results show that optimizing the output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.
    LanguageEnglish
    Article numberTCDS-2018-0127.R2
    JournalIEEE Transactions on Cognitive and Developmental Systems
    Publication statusAccepted/In press - 29 Mar 2019

    Fingerprint

    Neurons
    Learning algorithms

    Keywords

    • spiking neuron
    • spiking network

    Cite this

    @article{569f8a904097408a8eb0630ea9845d70,
    title = "Optimization of output spike train encoding for a spiking neuron based on its spatiotemporal input pattern",
    abstract = "A common learning task for a spiking neuron is to map a spatiotemporal input pattern to a target output spike train. There is no prescribed method for selection of the target output spike train. However, the precise spiking pattern of the target output spike train (output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target output spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial sub-optimal output encoding during different learning epochs to find the optimal output encoding. A time varying value of a local event called a spike trace is used to calculate the amount of a required adjustment. The Remote Supervised Method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized output encoding (optimized desired spikes). Experimental results show that optimizing the output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized output encoding in classification tasks and the results revealed improvements up to 16.5{\%} in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90{\%} to 100{\%}.",
    keywords = "spiking neuron, spiking network",
    author = "T.Martin McGinnity and Georgina Cosma and Aboozar Takerkhani",
    year = "2019",
    month = "3",
    day = "29",
    language = "English",
    journal = "IEEE Transactions on Cognitive and Developmental Systems",
    issn = "2379-8920",

    }

    TY - JOUR

    T1 - Optimization of output spike train encoding for a spiking neuron based on its spatiotemporal input pattern

    AU - McGinnity, T.Martin

    AU - Cosma, Georgina

    AU - Takerkhani, Aboozar

    PY - 2019/3/29

    Y1 - 2019/3/29

    N2 - A common learning task for a spiking neuron is to map a spatiotemporal input pattern to a target output spike train. There is no prescribed method for selection of the target output spike train. However, the precise spiking pattern of the target output spike train (output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target output spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial sub-optimal output encoding during different learning epochs to find the optimal output encoding. A time varying value of a local event called a spike trace is used to calculate the amount of a required adjustment. The Remote Supervised Method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized output encoding (optimized desired spikes). Experimental results show that optimizing the output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.

    AB - A common learning task for a spiking neuron is to map a spatiotemporal input pattern to a target output spike train. There is no prescribed method for selection of the target output spike train. However, the precise spiking pattern of the target output spike train (output encoding) can affect the learning performance of the spiking neuron. Therefore, systematic methods of finding the optimum spiking pattern for a target output spike train that can be learned by spiking neurons are needed. Here, a method is proposed to adaptively adjust an initial sub-optimal output encoding during different learning epochs to find the optimal output encoding. A time varying value of a local event called a spike trace is used to calculate the amount of a required adjustment. The Remote Supervised Method (ReSuMe) learning algorithm is used to train the weights, and the proposed method is used for finding optimized output encoding (optimized desired spikes). Experimental results show that optimizing the output encoding during the learning phase increases the accuracy. The proposed method was applied to find optimized output encoding in classification tasks and the results revealed improvements up to 16.5% in accuracy compared to when using the non-adapted method. It also increases the accuracy in a classification task from 90% to 100%.

    KW - spiking neuron

    KW - spiking network

    M3 - Article

    JO - IEEE Transactions on Cognitive and Developmental Systems

    T2 - IEEE Transactions on Cognitive and Developmental Systems

    JF - IEEE Transactions on Cognitive and Developmental Systems

    SN - 2379-8920

    M1 - TCDS-2018-0127.R2

    ER -