We show instances where parts of algorithms similar to backpropagation respectively projection le... more We show instances where parts of algorithms similar to backpropagation respectively projection learning algorithms have been implemented via feedback in neural systems. The corresponding algorithms, with the same or a similar mathematical expression, do not minimize an error in the output space of the network, but rather in the input space of the network, via a comparison between the function to be approximated and the current approximation executed by the network, which is fed back to the input space: We argue that numerous interlayer resp. intracortical feedback connections, e.g. in the visual primary system of mammals, could serve exactly this purpose. We introduce the paradigm with linear operators for illustration purposes, show the extension to nonlinear operators in function space, introduce projection learning, and discuss future work
Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolut... more Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolution de deux problemes de vision bas niveau, la restauration d'images bruitees et la detection de zones urbaines dans les images-satellite. Le premier probleme, vu comme un compromis a trouver entre deux jeux de contraintes, est resolu par modelisation a l'aide d'une trame de neuro-oscillateurs couples qui convergent vers la solution recherchee. Le deuxieme probleme est resolu par un pretraitement de l'image suivi d'une classification avec un reseau neuromimetique multicouche utilisant un nouveau type d'apprentissage supervise
Neurocomputation in Remote Sensing Data Analysis, 1997
In this paper, we present a hybrid method for preprocessing and classification of satellite image... more In this paper, we present a hybrid method for preprocessing and classification of satellite images. The preprocessing consists of computing texture measures of the images and initialising the probabilities of pixels belonging to different land-cover classes. The objective of the preprocessing is twofold: increasing discrimination power and removing irrelevant characteristics. The classification process consists of assigning a class to each pixel, with a special interest in detecting urban areas as completely as possible with the aid of a priori knowledge. This interest stems from the possible requirement of detecting urban areas on satellite images (even small villages in the countryside) while ignoring some classes (such as parks) in cities. We shall show how this requirement is translated into constraints imposed in our classification process. Experimental results are illustrated through a SPOT image containing a coastal town.
Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolut... more Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolution de deux problemes de vision bas niveau, la restauration d'images bruitees et la detection de zones urbaines dans les images-satellite. Le premier probleme, vu comme un compromis a trouver entre deux jeux de contraintes, est resolu par modelisation a l'aide d'une trame de neuro-oscillateurs couples qui convergent vers la solution recherchee. Le deuxieme probleme est resolu par un pretraitement de l'image suivi d'une classification avec un reseau neuromimetique multicouche utilisant un nouveau type d'apprentissage supervise
We have presented in (Weigl et al. 1992 - 1993 b) a paradigm in which we consider neural networks... more We have presented in (Weigl et al. 1992 - 1993 b) a paradigm in which we consider neural networks such as Multi-layer Perceptrons as bases in a function space; the basis functions are the functions computed by the hidden layer neurons, and the function approximated by the network is the projection of the function to be approximated onto the manifold spanned by these basis functions. We have presented a learning algorithm based on that paradigm, which consists in shifting the manifold spanned by that base in function space in such a way that the distance to the function to be approximated is minimal.
We show instances where parts of algorithms similar to backpropagation respectively projection le... more We show instances where parts of algorithms similar to backpropagation respectively projection learning algorithms have been implemented via feedback in neural systems. The corresponding algorithms, with the same or a similar mathematical expression, do not minimize an error in the output space of the network, but rather in the input space of the network, via a comparison between the function to be approximated and the current approximation executed by the network, which is fed back to the input space: We argue that numerous interlayer resp. intracortical feedback connections, e.g. in the visual primary system of mammals, could serve exactly this purpose. We introduce the paradigm with linear operators for illustration purposes, show the extension to nonlinear operators in function space, introduce projection learning, and discuss future work
We show instances where parts of algorithms similar to backpropagation respectively projection le... more We show instances where parts of algorithms similar to backpropagation respectively projection learning algorithms have been implemented via feedback in neural systems. The corresponding algorithms, with the same or a similar mathematical expression, do not minimize an error in the output space of the network, but rather in the input space of the network, via a comparison between the function to be approximated and the current approximation executed by the network, which is fed back to the input space: We argue that numerous interlayer resp. intracortical feedback connections, e.g. in the visual primary system of mammals, could serve exactly this purpose. We introduce the paradigm with linear operators for illustration purposes, show the extension to nonlinear operators in function space, introduce projection learning, and discuss future work
Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolut... more Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolution de deux problemes de vision bas niveau, la restauration d'images bruitees et la detection de zones urbaines dans les images-satellite. Le premier probleme, vu comme un compromis a trouver entre deux jeux de contraintes, est resolu par modelisation a l'aide d'une trame de neuro-oscillateurs couples qui convergent vers la solution recherchee. Le deuxieme probleme est resolu par un pretraitement de l'image suivi d'une classification avec un reseau neuromimetique multicouche utilisant un nouveau type d'apprentissage supervise
Neurocomputation in Remote Sensing Data Analysis, 1997
In this paper, we present a hybrid method for preprocessing and classification of satellite image... more In this paper, we present a hybrid method for preprocessing and classification of satellite images. The preprocessing consists of computing texture measures of the images and initialising the probabilities of pixels belonging to different land-cover classes. The objective of the preprocessing is twofold: increasing discrimination power and removing irrelevant characteristics. The classification process consists of assigning a class to each pixel, with a special interest in detecting urban areas as completely as possible with the aid of a priori knowledge. This interest stems from the possible requirement of detecting urban areas on satellite images (even small villages in the countryside) while ignoring some classes (such as parks) in cities. We shall show how this requirement is translated into constraints imposed in our classification process. Experimental results are illustrated through a SPOT image containing a coastal town.
Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolut... more Nous avons applique des solutions utilisees par des systemes biologiques de neurones a la resolution de deux problemes de vision bas niveau, la restauration d'images bruitees et la detection de zones urbaines dans les images-satellite. Le premier probleme, vu comme un compromis a trouver entre deux jeux de contraintes, est resolu par modelisation a l'aide d'une trame de neuro-oscillateurs couples qui convergent vers la solution recherchee. Le deuxieme probleme est resolu par un pretraitement de l'image suivi d'une classification avec un reseau neuromimetique multicouche utilisant un nouveau type d'apprentissage supervise
We have presented in (Weigl et al. 1992 - 1993 b) a paradigm in which we consider neural networks... more We have presented in (Weigl et al. 1992 - 1993 b) a paradigm in which we consider neural networks such as Multi-layer Perceptrons as bases in a function space; the basis functions are the functions computed by the hidden layer neurons, and the function approximated by the network is the projection of the function to be approximated onto the manifold spanned by these basis functions. We have presented a learning algorithm based on that paradigm, which consists in shifting the manifold spanned by that base in function space in such a way that the distance to the function to be approximated is minimal.
We show instances where parts of algorithms similar to backpropagation respectively projection le... more We show instances where parts of algorithms similar to backpropagation respectively projection learning algorithms have been implemented via feedback in neural systems. The corresponding algorithms, with the same or a similar mathematical expression, do not minimize an error in the output space of the network, but rather in the input space of the network, via a comparison between the function to be approximated and the current approximation executed by the network, which is fed back to the input space: We argue that numerous interlayer resp. intracortical feedback connections, e.g. in the visual primary system of mammals, could serve exactly this purpose. We introduce the paradigm with linear operators for illustration purposes, show the extension to nonlinear operators in function space, introduce projection learning, and discuss future work
Uploads
Papers by Konrad Weigl