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.
Optical neural networks for classification into arbitrary classes
1996-01-01
39840 byte
Conference paper
Electronic Resource
English
Optical Neural Networks for Classification into Arbitrary Classes
British Library Conference Proceedings | 1996
|Robust classification of arbitrary object classes based on hierarchical spatial feature-matching
British Library Online Contents | 1997
|Optimal metrics in classification problems with ordered features and an arbitrary number of classes
British Library Online Contents | 2009
|Classification of vehicles using neural networks
Tema Archive | 1993
|Bus line classification using neural networks
Elsevier | 2014
|