A neural cocktail-party processor
Biological Cybernetics
1994 Special Issue: Winner-take-all networks for physiological models of competitive learning
Neural Networks - Special issue: models of neurodynamics and behavior
Image segmentation based on oscillatory correlation
Neural Computation
Object selection based on oscillatory correlation
Neural Networks
Preintegration lateral inhibition enhances unsupervised learning
Neural Computation
A Competitive-Layer Model for Feature Binding and Sensory Segmentation
Neural Computation
On Connectedness: A Solution Based on Oscillatory Correlation
Neural Computation
Figure–Ground Segregation in a Recurrent Network Architecture
Journal of Cognitive Neuroscience
Motion segmentation based on motion/brightness integration and oscillatory correlation
IEEE Transactions on Neural Networks
Texture segmentation using Gaussian-Markov random fields and neural oscillator networks
IEEE Transactions on Neural Networks
Modelling the statistical processing of visual information
Neurocomputing
Selectivity and Stability via Dendritic Nonlinearity
Neural Computation
A Computational Model of Saliency Map Read-Out during Visual Search
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Hi-index | 0.01 |
A recurrent network is proposed with the ability to bind image features into a unified surface representation within a single layer and without capacity limitations or border effects. A group of cells belonging to the same object or surface is labeled with the same activity amplitude, while cells in different groups are kept segregated due to lateral inhibition. Labeling is achieved by activity spreading through local excitatory connections. In order to prevent uncontrolled spreading, a separate network computes the intensity difference between neighboring locations and signals the presence of the surface boundary, which constrains local excitation. The quality of surface representation is not compromised due to the self-excitation.The model is also applied on gray-level images. In order to remove small, noisy regions, a feedforward network is proposed that computes the size of surfaces. Size estimation is based on the difference of dendritic inhibition in lateral excitatory and inhibitory pathways, which allows the network to selectively integrate signals only from cells with the same activity amplitude. When the output of the size estimation network is combined with the recurrent network, good segmentation results are obtained. Both networks are based on biophysically realistic mechanisms such as dendritic inhibition and multiplicative integration among different dendritic branches.