In this paper we address the problem of optimal parameter selection for a Multilayer Perceptron by means of a neural network with only one hidden layer that uses the "back propagation" algorithm over relatively simple classification problems in two dimensions (input patterns with only two variables). We will show graphically the direct relation existing between the increasing complexity regions (classes) and the necessity to add more neurons in the hidden layer. At the end, we summarize our findings by means of parameter selection recommendations in order to avoid the tedious and blind "trial and error" method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Toward Optimal Parameter Selection for the Multi-layer Perceptron Artificial Neural Network




    Publication date :

    2013-11-01


    Size :

    470903 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Automatic Incident Detection on Freeways Using Multi-Layer Perceptron Neural Network

    Wen, H. / Yang, Z. / Jiang, G. et al. | British Library Conference Proceedings | 2002


    Automatic Incident Detection on Freeways Using Multi-Layer Perceptron Neural Network

    Wen, Huimin / Yang, Zhaosheng / Jiang, Guiyan et al. | ASCE | 2002


    Thermal Conductivity Prediction of Pure Liquids Using Multi-Layer Perceptron Neural Network

    Najafi, Alireza / Hamzehie, Mohammad Ehsan / Najibi, Hesam et al. | AIAA | 2014


    Multi-Layer Perceptron Based Lung Tumor Classification

    Potghan, Sneha / Rajamenakshi, R. / Bhise, Archana | IEEE | 2018