Holger Bosch
University of Geneva
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Holger Bosch.
Journal of Cognitive Neuroscience | 2002
Pieter R. Roelfsema; Victor A. F. Lamme; Henk Spekreijse; Holger Bosch
Here we propose a model of how the visual brain segregates textured scenes into figures and background. During texture segregation, locations where the properties of texture elements change abruptly are assigned to boundaries, whereas image regions that are relatively homogeneous are grouped together. Boundary detection and grouping of image regions require different connection schemes, which are accommodated in a single network architecture by implementing them in different layers. As a result, all units carry signals related to boundary detection as well as grouping of image regions, in accordance with cortical physiology. Boundaries yield an early enhancement of network responses, but at a later point, an entire figural region is grouped together, because units that respond to it are labeled with enhanced activity. The model predicts which image regions are preferentially perceived as figure or as background and reproduces the spatio-temporal profile of neuronal activity in the visual cortex during texture segregation in intact animals, as well as in animals with cortical lesions.
Neural Networks | 1999
Arnaud Tonnelier; Sylvain Meignen; Holger Bosch; Jacques Demongeot
We have used continuous and discrete-time versions of a neural oscillator model to analyze how various types of synaptic connections between oscillators affect synchronization and desynchronization phenomena. First, we present a synthesis of the mathematical properties of both neural oscillator versions. Then, we show that the choice of parameters leads to a relationship between the two versions. Finally, we achieve the coupling of two oscillators in order to study how synaptic connections affect the phase lag. With this in mind, we state some of the results for the continuous-time model. The second part of this paper deals with the behavior of neural networks comprising connected oscillators, which involves looking at the conditions for desynchronization of a totally synchronized oscillator net. Such a study has been carried out both for a fully and for a sparsely connected network. This leads to the observation that some architectures enable proper desynchronization when the size of the network is large. While searching for the conditions for desynchronization, we have discovered that a macroscopic description of the network is sometimes possible. To conclude, we discuss the advantages and the limitations of this macroscopic approach.
Neural Networks | 1998
Holger Bosch; Franz J. Kurfess
In this paper, the memory capacity of incompletely connected associative memories is investigated. First, the capacity is derived for memories with fixed parameters. Optimization of the parameters yields a maximum capacity between 0.53 and 0.69 for hetero-association and half of it for autoassociation improving previously reported results. The maximum capacity grows with increasing connectivity of the memory and requires sparse input and output patterns. Further, parameters can be chosen in such a way that the information content per pattern asymptotically approaches 1 with growing size of the memory.
international work conference on artificial and natural neural networks | 1997
Abderrahim Labbi; Ruggero Milanese; Holger Bosch
In this paper we adopt a temporal coding approach to neuronal modeling of the visual cortex, using oscillations. We propose a hierarchy of three processing modules corresponding to different levels of representation. The first layer encodes the input image (stimulus) into an array of units, while the second layer consists of a network of FitzHugh-Nagumo oscillators. The dynamical behaviour of the coupled oscillators is rigorously investigated and a stimulus-driven synchronization theorem is derived. However, this module reveals itself insufficient to correctly encode and segregate different objects when they have similar gray-levels in the input image. Therefore, a third layer connected in a feedback loop with the oscillators is added. This ensures synchronization (resp. desynchronization) of neuron ensembles representing the same (resp. a different) object. Simulation results are presented using synthetic as well as real and noisy gray-level images.
International Journal of Neural Systems | 2001
Abderrahim Labbi; Holger Bosch; Christian Pellegrini
This paper addresses the problem of image classification using local information which is aggregated to provide global representation of different image classes. Local information is adaptively extracted from an image database using Independent Component Analysis (ICA) which provides a set of localized, oriented, and band-pass filters selective to independent features of the images. Local representation using ICA techniques has been previously investigated by several researchers. However, very little work has been done on further use of these representations to provide more complex and global description of images. In this paper, we present an algorithm which uses the energy of a minimal set of ICA filters to provide class-specific signatures which are shown to be strongly discriminant. Computer simulations are carried on two image databases, one consisting of five classes--referred to as categories--(buildings, rooms, mountains, forests and beaches) and one consisting of a set of 30 objects from multiple views for viewpoint invariant object recognition. The classification performance of the algorithm using both Independent and Principal Component Analyses are reported and discussed.
International Journal of Bifurcation and Chaos | 1999
Abderrahim Labbi; Ruggero Milanese; Holger Bosch
In this paper, we describe the asymptotic behavior of a network of locally connected oscillators. The main result concerns asymptotic synchronization. The presented study is stated in the framework of neuronal modeling of visual object segmentation using oscillatory correlation. The practical motivations of the synchronization analysis are based on neurophysiological experiments which led to the assumptions that existence of temporal coding schemes in the brain by which neurons, with oscillatory dynamics, coding for the same coherent object synchronize their activities, while neurons coding for different objects oscillate with nonzero phase lags. The oscillator model considered is the FitzHugh–Nagumo neuron model. We restrict our study to the mathematical analysis of a network of such neurons. We firstly show the motivations and suitability of choosing FitzHugh–Nagumo oscillator, mainly for stimulus coding purposes, and then we give sufficient conditions on the coupling parameters which guarantee asymptotic synchronization of oscillators receiving the same external stimulation (input). We have used networks of such oscillators to design a layered architecture for object segmentation in gray-level images. Due to space limitations, description of this architecture and simulation results are briefly referred to by the end of the paper.
Archive | 1998
Holger Bosch; Ruggero Milanese; Abderrahim Labbi; Jacques Demongeot
A neural oscillator capable of processing graded inputs is studied. The oscillator has two functional modes controlled by an external signal and codes information either by the amplitude of its oscillations or by the coordinates of its fixed point. Excitatory and inhibitory connections between coupled oscillators control their phase relations. Simulations and theoretical analyses show that any desired phase relation can be induced by an appropriate choice of connections. The capabilities of the oscillator model are demonstrated in an architecture for gray-level image segmentation.
international conference on neural information processing | 1999
A. Labbi; Holger Bosch; Christian Pellegrini; W. Gerstner
This paper addresses the problem of image categorization using local sensory information which is aggregated into global cortical-like representations of different image categories. Local information is adaptively extracted from an image database using independent component analysis (ICA) which provides a set of localized, oriented, and band-pass filters selective to the most independent features of the different categories. Such local representations have been computationally investigated by several researchers, and have also been experimentally observed as characteristics of simple cell receptive fields in the primary visual cortex. However, little work has been done on further use of these representations to provide more complex and global description of images. In this paper, we present an algorithm which uses the energy of a minimal set of filters to provide category-specific signatures which are shown to be strongly discriminant. Computer simulations are carried on an image database consisting of three categories (faces, leaves, and buildings). The categorization performances of the algorithm using ICA and PCA filters are reported. It is mainly shown that considering a small number of PCA filters leads to a performance which is not significantly improved by considering other PCA filters, however, considering additional ICA filters increases performance due to the fact that each additional filter carries additional information (in the entropy sense).
Nonlinear Analysis-theory Methods & Applications | 2001
Abderrahim Labbi; Ruggero Milanese; Holger Bosch
Archive | 1998
Holger Bosch; Ruggero Milanese; Abderrahim Labbi