Begoña Pino

Time series analysis using normalized PG-RBF network with regression weights

This paper proposes a framework for constructing and training a radial basis function (RBF) neural network. For this purpose, a sequential learning algorithm is presented to adapt the structure of the network, in which it is possible to create a new hidden unit and also to detect and remove inactive units. The structure of the Gaussian functions is modified using a pseudo-Gaussian function (PG) in which two scaling parameters σ are introduced, which eliminates the symmetry restriction and provides the neurons in the hidden layer with greater flexibility with respect to function approximation. Other important characteristics of the proposed neural system are that the activation of the hidden neurons is normalized which, as described in the bibliography, provides a better performance than nonnormalization and instead of using a single parameter for the output weights, these are functions of the input variables which leads to a significant reduction in the number of hidden units compared to the classical RBF network. Finally, we examine the result of applying the proposed algorithm to time series prediction.

Online global learning in direct fuzzy controllers

A novel approach to achieve real-time global learning in fuzzy controllers is proposed. Both the rule consequents and the membership functions defined in the premises of the fuzzy rules are tuned using a one-step algorithm, which is capable of controlling nonlinear plants with no prior offline training. Direct control is achieved by means of two auxiliary systems: The first one is responsible for adapting the consequents of the main controllers rules to minimize the error arising at the plant output, while the second auxiliary system compiles real input-output data obtained from the plant. The system then learns in real time from these data taking into account, not the current state of the plant but rather the global identification performed. Simulation results show that this approach leads to an enhanced control policy thanks to the global learning performed, avoiding overfitting.

A Computational Framework for Realistic Retina Modeling

Computational simulations of the retina have led to valuable insights about the biophysics of its neuronal activity and processing principles. A great number of retina models have been proposed to reproduce the behavioral diversity of the different visual processing pathways. While many of these models share common computational stages, previous efforts have been more focused on fitting specific retina functions rather than generalizing them beyond a particular model. Here, we define a set of computational retinal microcircuits that can be used as basic building blocks for the modeling of different retina mechanisms. To validate the hypothesis that similar processing structures may be repeatedly found in different retina functions, we implemented a series of retina models simply by combining these computational retinal microcircuits. Accuracy of the retina models for capturing neural behavior was assessed by fitting published electrophysiological recordings that characterize some of the best-known phenomena observed in the retina: adaptation to the mean light intensity and temporal contrast, and differential motion sensitivity. The retinal microcircuits are part of a new software platform for efficient computational retina modeling from single-cell to large-scale levels. It includes an interface with spiking neural networks that allows simulation of the spiking response of ganglion cells and integration with models of higher visual areas.

Automatic generation of bio-inspired retina-like processing hardware

This paper describes a tool devised for automatic design of bioinspired visual processing models using reconfigurable digital hardware. The whole system is indicated for the analysis of vision models, especially those with real–time requirements. We achieve a synthesizable FPGA/ASIC design starting from a high level description of a retina, which is made and simulated through an ad-hoc program. Our tool allows a thorough simulation of the visual model at different abstraction levels, from functional simulation of the visual specifications up to hardware-oriented simulation of the developed FPGA model. The main objective of this work is to build a portable and flexible system for a visual neuro-prosthesis and to stimulate efficiently an array of intra–cortical implanted microelectrodes. A set of parameters can be adjusted in every step of the design flow in order to maximize the design flexibility of the model. Furthermore these parameters allow the different scientists who have to deal with the development to modify a well known characteristic.

Real-Time Visual Saliency Architecture for FPGA With Top-Down Attention Modulation

Biological vision uses attention to reduce the visual bandwidth simplifying the higher-level processing. This paper presents a model and its hardware real-time architecture in a field programmable gate array (FPGA) to be integrated in a robotic system that emulates this powerful biological process. It is based on the combination of bottom-up saliency and top-down task-dependent modulation. The bottom-up stream is deployed including local energy, orientation, color opponencies, and motion maps. The most novel part of this work is the saliency modulation by two high-level features: 1) optical flow and 2) disparity. Furthermore, the influence of the features may be adjusted depending on the application. The proposed system reaches 180 fps for 640 × 480 resolution. Finally, an example shows its modulation potential for driving assistance systems.

A digital implementation of self-organizing maps

A digital implementation of self-organizing maps is presented. The chip designed includes 32 neurons with 1024 16-bit weights and 8-bit inputs. Each neutron performs bit-serial processing to minimize the occupied silicon area. Several chips can be interconnected to expand the number of neurons in the network. The number of inputs per neuron depends on the internal weight memory size. The dimensionality of the network the neighbourhood topology and the rate at which the neighbouring cells learn, are programmable. The design was realised using the cells of the ES2 ecpd10 Library and simulated with Verilog. The estimated operation speed is 0.7 MCUPS/mm/sup 2/ during the learning phase, and 1.95 MCPS/mm/sup 2/ during the recall phase.

Design and evaluation of a reconfigurable digital architecture for self-organizing maps

A digital SIMD architecture to implement Self-Organizing Maps is presented. Custom bit-serial processing elements have been designed not only to obtain a high integration density (an area of 0.06 mm/sup 2/ per PE is estimated for a 0.25 /spl mu/m process and a standard cell design) but also to improve flexibility. The dimensionality of the map, the topological neighbourhood and the kernel function shape are programmable. A modular approach allows several neurochips to be interconnected to expand both the number of neurons and the number of synapses per neuron, performing a mixed synapse/neuron parallelism. In a system composed of a fixed number of neurochips, the number of neurons and synapses physically implemented can be reconfigured in order to achieve the optimal exploitation of hardware resources. The performance of the proposed architecture for fully implemented networks and virtual nets has been evaluated. A significant speedup improvement is achieved in comparison with a similar architecture without synapse parallelism.

First Stage of a Human Visual System Simulator: The Retina

We propose a configurable simulation platform that reproduces the analog neural behavior of different models of the Human Visual System at the early stages. Our software can simulate efficiently many of the biological mechanisms found in retina cells, such as chromatic opponency in the red-green and blue-yellow pathways, signal gathering through chemical synapses and gap junctions or variations in the neuron density and the receptive field size with eccentricity. Based on an image-processing approach, simulated neurons can perform spatiotemporal and color processing of the input visual stimuli generating the visual maps of every intermediate stage, which correspond to membrane potentials and synaptic currents. An interface with neural network simulators has been implemented, which allows to reproduce the spiking output of some specific cells, such as ganglion cells, and integrate the platform with models of higher brain areas. Simulations of different retina models related to the color opponent mechanisms, obtained from electro-physiological experiments, show the capability of the platform to reproduce their neural response.

Visual training and emotional state of people with retinitis pigmentosa

The purpose of the study was to improve the visual functioning of people with restriction in contrast sensitivity (CS), such as retinitis pigmentosa (RP), by means of a visual training program. Twenty-six volunteers with RP participated, distributed in two groups: 15 who made up the experimental group (who received the training program) and 11 who participated as a control group (without training). Participants were evaluated before beginning training, on completion, and 3 mo following completion for CS with the Pelli-Robson Contrast Sensitivity (P&R) test, visual functioning with the Visual Function Questionnaire (VFQ), and in emotional state with the Beck Depression Inventory (BDI). The training program is based on software that generates luminous stimuli of varying duration and intensity and registers the stimuli perceived by the subject. The outcomes showed significant differences posttraining in the experimental group in depression (F1,14 = 5.42; p < 0.04), VFQ (Z = -2.27; p < 0.02), and P&R in the right eye (Z = -1.99; p < 0.046) and left eye (Z = -2.30; p < 0.02) but not in binocular (Z = -0.96; p < 0.34). The outcomes showed that the experimental group made significant progress in all variables and these effects remained after 3 mo, which suggests that the program could be a helpful addition to RP rehabilitation and help mitigate the damage.

Real-time Architecture for Robust Motion Estimation under Varying Illumination Conditions

Motion estimation from image sequences is a complex problem which requires high computing resources and is highly affected by changes in the illumination conditions in most of the existing approaches. In this contribution we present a high performance system that deals with this limitation. Robustness to varying illumination conditions is achieved by a novel technique that combines a gradient-based optical flow method with a non-parametric image transformation based on the Rank transform. The paper describes this method and quantitatively evaluates its robustness to different illumination changing patterns. This technique has been successfully implemented in a real-time system using reconfigurable hardware. Our contribution presents the computing architecture, including the resources consumption and the obtained performance. The final system is a real-time device capable to computing motion sequences in real-time even in conditions with significant illumination changes. The robustness of the proposed system facilitates its use in multiple potential application fields.