Classification systems, which have long been realized through rule-based systems, are now being implemented with neural-expert system hybrids because of the well known difficulties associated with the formation of rules and the ease with which neural networks can capture the relationships between attributes and classifications. Backpropagation, which is a commonly used neural network training algorithm, suffers from slow training and the possibility of local minima trapping. In this paper we propose a new neural network training algorithm, ternary synaptic weights (TSW) algorithm, which offers fast, guaranteed learning and automatic topology determination. Also, it provides an insight into the interrelationships between the attributes and the classifications, which is very suitable for hybridization of neural networks and expert systems. Furthermore, it takes don't care attributes, which are an essential part of rule-based systems, into consideration during training.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Ternary synaptic weights algorithm: neural network training with don't care attributes


    Contributors:
    Ulgen, F. (author) / Akamatsu, N. (author)


    Publication date :

    1994-01-01


    Size :

    256400 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Ternary Synaptic Weights Algorithm: Neural Network Training With Don't Care Attributes

    Ulgen, F. / Akamatsu, N. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994


    A Learning Algorithm of Fuzzy Neural Networks with Fuzzy Weights

    Ishibuchi, H. / Kwon, K. / Tanaka, H. | British Library Online Contents | 1993


    Training Ternary Neural Networks By Rectified L2 Regularization

    Han, Qiankun / Fan, Yuanning / Ge, Jiexian et al. | IEEE | 2019


    Memristive synaptic crosstalk effects on Hopfield neural network

    Zhang, Yapeng / Dong, Enzeng / Tong, Jigang et al. | British Library Conference Proceedings | 2022


    Fuzzy Neural Networks with Fuzzy Weights

    Ishibuchi, H. / Okada, H. / Tanaka, H. | British Library Online Contents | 1993