PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Some important concepts of 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.
H. H. Arsenault,S. Chang,Philippe Gagne, andOscar Gualdron Gonzalez
"Optical neural networks for classification into arbitrary classes", Proc. SPIE 10287, Optoelectronic Devices and Systems for Processing: A Critical Review, 1028706 (9 August 1996); https://doi.org/10.1117/12.259697
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
H. H. Arsenault, S. Chang, Philippe Gagne, Oscar Gualdron Gonzalez, "Optical neural networks for classification into arbitrary classes," Proc. SPIE 10287, Optoelectronic Devices and Systems for Processing: A Critical Review, 1028706 (9 August 1996); https://doi.org/10.1117/12.259697