Alicia d’Anjou

Energy efficiency of information transmission by electrically coupled neurons.

The generation of spikes by neurons is energetically a costly process. This paper studies the consumption of energy and the information entropy in the signalling activity of a model neuron both when it is supposed isolated and when it is coupled to another neuron by an electrical synapse. The neuron has been modelled by a four-dimensional Hindmarsh-Rose type kinetic model for which an energy function has been deduced. For the isolated neuron values of energy consumption and information entropy at different signalling regimes have been computed. For two neurons coupled by a gap junction we have analyzed the roles of the membrane and synapse in the contribution of the energy that is required for their organized signalling. Computational results are provided for cases of identical and nonidentical neurons coupled by unidirectional and bidirectional gap junctions. One relevant result is that there are values of the coupling strength at which the organized signalling of two neurons induced by the gap junction takes place at relatively low values of energy consumption and the ratio of mutual information to energy consumption is relatively high. Therefore, communicating at these coupling values could be energetically the most efficient option.

A Sensitivity Analysis of the Self Organizing Maps as an AdaptiveOne-pass Non-stationary Clustering Algorithm: the Case of ColorQuantization of Image Sequences

In this paper we study the sensitivity of the Self Organizing Map to several parameters in the context of the one-pass adaptive computation of cluster representatives over non-stationary data. The paradigm of Non-stationary Clustering is represented by the problem of Color Quantization of image sequences.

Efficient synchronization of structurally adaptive coupled Hindmarsh–Rose neurons

Abstract The use of spikes to carry information between brain areas implies complete or partial synchronization of the neurons involved. The degree of synchronization reached by two coupled systems and the energy cost of maintaining their synchronized behavior is highly dependent on the nature of the systems. For non-identical systems the maintenance of a synchronized regime is energetically a costly process. In this work, we study conditions under which two non-identical electrically coupled neurons can reach an efficient regime of synchronization at low energy cost. We show that the energy consumption required to keep the synchronized regime can be spontaneously reduced if the receiving neuron has adaptive mechanisms able to bring its biological parameters closer in value to the corresponding ones in the sending neuron.

Feature Extraction by Linear Spectral Unmixing

Linear Spectral Unmixing (LSU) has been proposed for the analysis of hyperspectral images, to compute the fractional contribution of the detected endmembers to each pixel in the image. In this paper we propose that the fractional abundance coefficients to be used as features for the supervised classification of the pixels. Thus we compare them with two well-known linear feature extraction algorithms: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). A specific problem of LSU is the determination of the endmembers, to this end we employ two approaches, the Convex Cone Analysis and another one based on the detection of morphological independence.

Experiments of Fast Learning with High Order Boltzmann Machines

This work reports the results obtained with the application of High Order Boltzmann Machines without hidden units to construct classifiers for some problems that represent different learning paradigms. The Boltzmann Machine weight updating algorithm remains the same even when some of the units can take values in a discrete set or in a continuous interval. The absence of hidden units and the restriction to classification problems allows for the estimation of the connection statistics, without the computational cost involved in the application of simulated annealing. In this setting, the learning process can be sped up several orders of magnitude with no appreciable loss of quality of the results obtained.

Further results on swarms solving graph coloring

We have proposed the mapping of graph coloring problems into swarm dynamics. Empirical evidence that flock steering behaviors augmented with the notion of hostility (enmity and friendliness) are enough to perform efficiently the task of coloring the nodes of graphs even in the case 3-coloration hard graph topologies. We discuss here what are the minimal cognitive capabilities that allow the emergent behavior of swarms to solve such NP-complete problem without mediating an explicit knowledge representation.

Nonzero error synchronization of chaotic systems via dynamic coupling

Abstract When feedback coupling is used to synchronize arbitrary chaotic systems large enough constant interaction gains lead to nearly complete synchronization at quasi-zero error. This forced oscillatory regime takes place in a region of phase space that, although natural for the guiding system, can result to be impracticable as an operating region for the guided system. However, we show that a dynamic feedback coupling with the appropriate variable gain can lead to a fully synchronized regime at a given nonzero synchronization error, that is, with the guided system operating on a desired region of the phase space. Computational results for oscillators of the Lorenz and Rossler families are shown. The cost of maintaining a couple of oscillatory Lorenz systems synchronized at different constant values of the synchronization error has been evaluated. To do so, an energy-like function associated to the state of the guided system has been defined.

Morphological neural networks and vision based mobile robot navigation

Morphological Associative Memories (MAM) have been proposed for image denoising and pattern recognition. We have shown that they can be applied to other domains, like image retrieval and hyperspectral image unsupervised segmentation. In both cases the key idea is that Morphological Autoassociative Memories (MAAM) selective sensitivity to erosive and dilative noise can be applied to detect the morphological independence between patterns. The convex coordinates obtained by linear unmixing based on the sets of morphological independent patterns define a feature extraction process. These features may be useful either for pattern classification. We present some results on the task of visual landmark recognition for a mobile robot self-localization task.

A Color Transformation for Robust Detection of Color Landmarks in Robotic Contexts

We present in this work a robust color transformation which has been applied succesfully to natural scenes allowing the fast and precise segmentation of regions corresponding to color landmarks under uncontrolled lightning. The process is grounded in the the Dichromatic Reflexion Model (DRM) and the properties of the RGB space.

A Comparison of Experimental Results with an Evolution Strategy and Competitive Neural Networks for Near Real-Time Color Quantization of Image Sequences

Color quantization of image sequences is a case of non-stationary clustering problem. The approach we adopt to deal with this kind of problems is to propose adaptive algorithms to compute the cluster representatives. We have studied the application of Competitive Neural Networks and Evolution Strategies to the one-pass adaptive solution of this problem. One-pass adaptation is imposed by the near real-time constraint that we try to achieve. In this paper we propose a simple and effective evolution strategy for this task. Two kinds of competitive neural networks are also applied. Experimental results show that the proposed evolution strategy can produce results comparable to that of competitive neural networks.