Unsupervised segmentation with dynamical units
In this paper, we present a novel network to separate mixtures of inputs that have been
previously learned. A significant capability of the network is that it segments the components …
previously learned. A significant capability of the network is that it segments the components …
An objective function utilizing complex sparsity for efficient segmentation in multi‐layer oscillatory networks
A Ravishankar Rao, GA Cecchi - International Journal of Intelligent …, 2010 - emerald.com
Purpose–The purpose of this paper is to extend an analysis presented in earlier work which
investigated the dynamical behavior of a network of oscillatory units described by the …
investigated the dynamical behavior of a network of oscillatory units described by the …
A low complexity digital oscillatory neural network for image segmentation
D Fernandes, POA Navaux - Proceedings of the Fourth IEEE …, 2004 - ieeexplore.ieee.org
The use of oscillatory neural networks is a recent approach for applications in image
segmentation. In this context, the LEGION network is the most useful example. Two attractive …
segmentation. In this context, the LEGION network is the most useful example. Two attractive …
Methods for parameter identification in oscillatory networks and application to cortical and thalamic 600 Hz activity
L Leistritz, T Suesse, J Haueisen, B Hilgenfeld… - Journal of Physiology …, 2006 - Elsevier
Directed information transfer in the human brain occurs presumably by oscillations. As of yet,
most approaches for the analysis of these oscillations are based on time–frequency or …
most approaches for the analysis of these oscillations are based on time–frequency or …
Functional Constraints on Network Topology via Generalized Sparse Representations
A central issue in neuroscience is understanding to what extent the observed neural network
architectural patterns are the result of functional constraints, as opposed to evolutionary …
architectural patterns are the result of functional constraints, as opposed to evolutionary …