Combination of proposed modular, multilayer perceptron and algorithm for its operation recognizes new objects after relatively brief retraining sessions. (Perceptron is multilayer, feedforward artificial neural network fully connected and trained via back-propagation learning algorithm.) Knowledge pertaining to each object to be recognized resides in subnetwork of full network, therefore not necessary to retrain full network to recognize each new object.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Modular, Multilayer Perceptron


    Contributors:

    Published in:

    Publication date :

    1991-03-01



    Type of media :

    Miscellaneous


    Type of material :

    No indication


    Language :

    English




    Memristor crossbar based implementation of a multilayer perceptron

    Yakopcic, Chris / Taha, Tarek M. | IEEE | 2017


    A Spatio-Temporal Multilayer Perceptron for Gesture Recognition

    Holzbock, Adrian / Tsaregorodtsev, Alexander / Dawoud, Youssef et al. | IEEE | 2022


    Research on Sound Source Localization Algorithm Based on Multilayer Perceptron

    Zhang, Jinliang / Weng, Xianfeng / Zhou, Jing et al. | TIBKAT | 2021


    Research on Sound Source Localization Algorithm Based on Multilayer Perceptron

    Zhang, Jinliang / Weng, Xianfeng / Zhou, Jing et al. | Springer Verlag | 2021


    Long-Term Prediction of Lane Change Maneuver Through a Multilayer Perceptron

    Shou, Zhenyu / Wang, Ziran / Han, Kyungtae et al. | IEEE | 2020