Summary form only given. Some important concepts of optical neural networks are similarity, generalization, invariance and training. Some neural networks are supposed to be able to classify objects according to hidden similarities. All of those concepts are put into question by the consideration first put forward by Watenabe that from a purely logical point of view, similarity is a purely arbitrary concept. It can be shown that this implies that the notion of invariance is also arbitrary, that so-called hidden similarities and generalization cannot exist without some external criteria. Such criteria are either implicit in the training algorithms or must be imposed explicitly. This imposes severe limitations on what neural networks can accomplish. However there are some positive implications; neural networks can be designed to classify objects into arbitrary classes. Applications to optical neural networks and examples will be presented.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optical neural networks for classification into arbitrary classes


    Contributors:


    Publication date :

    1996-01-01


    Size :

    39840 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Optical Neural Networks for Classification into Arbitrary Classes

    IEEE; Lasers and Electro-Optics Society | British Library Conference Proceedings | 1996




    Classification of vehicles using neural networks

    Reijmers, J.J. | Tema Archive | 1993


    Bus line classification using neural networks

    Jiménez, Felipe / Serradilla, Francisco / Román, Alfonso et al. | Elsevier | 2014