This paper presents a new method for continuous and incremental learning and recognition based on self-organized incremental neural networks. It is available in the fluctuating environment where the number of recognition classes cannot be defined. In this method, the learning process and recognition process are not separated. This method can acquire concept when multiple feature vectors of new input object come, and then can recognize it using previously acquired concept. We experiment an examples of life-long semi-supervised learning tasks in real world. In the result, the proposed method was able to learn and recognize 104 objects incrementally, non-stop, and in real time.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Life-long Semi-supervised Learning: Continuation of Both Learning and Recognition


    Beteiligte:
    Kamiya, Youki (Autor:in) / Ishii, Toshiaki (Autor:in) / Hasegawa, Osamu (Autor:in)


    Erscheinungsdatum :

    2007-04-01


    Format / Umfang :

    467217 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Semi-supervised learning and feature evaluation for RGB-D object recognition

    Cheng, Y. / Zhao, X. / Huang, K. et al. | British Library Online Contents | 2015



    A Semi-Supervised Learning Algorithm for Growing Neural Gas in Face Recognition

    Zaki, S. M. / Yin, H. | British Library Online Contents | 2008


    Semi-Supervised Learning for Discrete Choice Models

    Yang, Jie / Shebalov, Sergey / Klabjan, Diego | IEEE | 2019


    Driver Distraction Detection Using Semi-Supervised Machine Learning

    Liu, Tianchi / Yang, Yan / Huang, Guang-Bin et al. | IEEE | 2016