Stochastic competitive learning in complex networks

Competitive learning is an important machine learning approach which is widely employed in artificial neural networks. In this paper, we present a rigorous definition of a new type of competitive learning scheme realized on large-scale networks. The model consists of several particles walking within the network and competing with each other to occupy as many nodes as possible, while attempting to reject intruder particles. The particle's walking rule is composed of a stochastic combination of random and preferential movements. The model has been applied to solve community detection and data clustering problems. Computer simulations reveal that the proposed technique presents high precision of community and cluster detections, as well as low computational complexity. Moreover, we have developed an efficient method for estimating the most likely number of clusters by using an evaluator index that monitors the information generated by the competition process itself. We hope this paper will provide an alternative way to the study of competitive learning.

An algoritmh for the estimation of 3D surfaces using competitive learning

This paper addresses the estimation of object boundaries from a set of 3D points. An extension of the constrained clustering algorithm developed by Abrantes and Marques in the context of edge linking is presented. The object surface is approximated using rectangular meshes and simplex nets. Centroid-based forces are used for attracting the model nodes towards the data, using competitive learning methods. It is shown that competitive learning improves the model performance in the presence of concavities and allows to discriminate close surfaces. The proposed model is evaluated using synthetic data and medical images (MRI and ultrasound images).

A distributed system for learning programming on-line

Several Web-based on-line judges or on-line programming trainers have been developed in order to allow students to train their programming skills. However, their pedagogical functionalities in the learning of programming have not been clearly defined. EduJudge is a project which aims to integrate the “UVA On-line Judge”, an existing on-line programming trainer with an important number of problems and users, into an effective educational environment consisting of the e-learning platform Moodle and the competitive learning tool QUESTOURnament. The result is the EduJudge system which allows teachers to apply different pedagogical approaches using a proven e-learning platform, makes problems easy to search through an effective search engine, and provides an automated evaluation of the solutions submitted to these problems. The final objective is to provide new learning strategies to motivate students and present programming as an easy and attractive challenge. EduJudge has been tried and tested in three algorithms and programming courses in three different Engineering degrees. The students’ motivation and satisfaction levels were analysed alongside the effects of the EduJudge system on students’ academic outcomes. Results indicate that both students and teachers found that among other multiple benefits the EduJudge system facilitates the learning process. Furthermore, the experi- ment also showed an improvement in students’ academic outcomes. It must be noted that the students’ level of satisfaction did not depend on their computer skills or their gender.

From e-learning systems to specialised e-learning services

Learning systems are evolving from component based and centralized architectures towards service oriented and decentralized architectures. The standardization of e-learning content and interoperability is a powerful force in this evolution. In this chapter we put in perspective the evolution of e-learning systems and standards, and argue that specialized services will play an important role in future learning systems, especially in those targeted for competitive learning.

Embodiment and Manipulation Learning Process for a Humanoid Hand

Babies are born with simple manipulation capabilities such as reflexes to perceived stimuli. Initial discoveries by babies are accidental until they become coordinated and curious enough to actively investigate their surroundings. This thesis explores the development of such primitive learning systems using an embodied light-weight hand with three fingers and a thumb. It is self-contained having four motors and 36 exteroceptor and proprioceptor sensors controlled by an on-palm microcontroller. Primitive manipulation is learned from sensory inputs using competitive learning, back-propagation algorithm and reinforcement learning strategies. This hand will be used for a humanoid being developed at the MIT Artificial Intelligence Laboratory.

Video target tracking by using competitive neural networks

A target tracking algorithm able to identify the position and to pursuit moving targets in video digital sequences is proposed in this paper. The proposed approach aims to track moving targets inside the vision field of a digital camera. The position and trajectory of the target are identified by using a neural network presenting competitive learning technique. The winning neuron is trained to approximate to the target and, then, pursuit it. A digital camera provides a sequence of images and the algorithm process those frames in real time tracking the moving target. The algorithm is performed both with black and white and multi-colored images to simulate real world situations. Results show the effectiveness of the proposed algorithm, since the neurons tracked the moving targets even if there is no pre-processing image analysis. Single and multiple moving targets are followed in real time.

Network-based stochastic semisupervised learning

Semisupervised learning is a machine learning approach that is able to employ both labeled and unlabeled samples in the training process. In this paper, we propose a semisupervised data classification model based on a combined random-preferential walk of particles in a network (graph) constructed from the input dataset. The particles of the same class cooperate among themselves, while the particles of different classes compete with each other to propagate class labels to the whole network. A rigorous model definition is provided via a nonlinear stochastic dynamical system and a mathematical analysis of its behavior is carried out. A numerical validation presented in this paper confirms the theoretical predictions. An interesting feature brought by the competitive-cooperative mechanism is that the proposed model can achieve good classification rates while exhibiting low computational complexity order in comparison to other network-based semisupervised algorithms. Computer simulations conducted on synthetic and real-world datasets reveal the effectiveness of the model.

The state of the nations:current and future developments in technology enhanced learning

Right across Europe technology is playing a vital part in enhancing learning for an increasingly diverse population of learners. Learning is increasingly flexible, social and mobile and supported by high quality multi-media resources. Institutional VLEs are seeing a shift towards open source products and these core systems are supplemented by a range of social and collaborative learning tools based on web 2.0 technologies. Learners undertaking field studies and those in the workplace are coming to expect that these off-campus experiences will also be technology-rich whether supported by institutional or user-owned devices. As well as keeping European businesses competitive, learning is seen as a means of increasing social mobility and supporting an agenda of social justice. For a number of years the EUNIS E-Learning Task Force (ELTF) has conducted snapshot surveys of e-learning across member institutions, collected case studies of good practice in e-learning see (Hayes, et al., 2009) in references, supported a group looking at the future of e-learning, and showcased the best of innovation in its e-learning Award. Now for the first time the ELTF membership has come together to undertake an analysis of developments in the member states and to assess what this might mean for the future. The group applied the techniques of World Café conversation and Scenario Thinking to develop its thoughts. The analysis is unashamedly qualitative and draws on expertise from leading universities across eight of the EUNIS member states. What emerges is interesting in terms of the common trends in developments in all of the nations and similarities in hopes and concerns about the future development of learning.

Bridging between programming exercises formats with BabeLO

Assessment plays a vital role in learning. This is certainly the case with assessment of computer programs, both in curricular and competitive learning. The lack of a standard – or at least a widely used format – creates a modern Ba- bel tower made of Learning Objects, of assessment items that cannot be shared among automatic assessment systems. These systems whose interoperability is hindered by the lack of a common format include contest management systems, evaluation engines, repositories of learning objects and authoring tools. A prag- matical approach to remedy this problem is to create a service to convert among existing formats. A kind of translation service specialized in programming prob- lems formats. To convert programming exercises on-the-fly among the most used formats is the purpose of the BabeLO – a service to cope with the existing Babel of Learning Object formats for programming exercises. BabeLO was designed as a service to act as a middleware in a network of systems typically used in auto- matic assessment of programs. It provides support for multiple exercise formats and can be used by: evaluation engines to assess exercises regardless of its format; repositories to import exercises from various sources; authoring systems to create exercises in multiple formats or based on exercises from other sources. This paper analyses several of existing formats to highlight both their differ- ences and their similar features. Based on this analysis it presents an approach to extensible format conversion. It presents also the features of PExIL, the pivotal format in which the conversion is based; and the function definitions of the proposed service – BabeLO. Details on the design and implementation of BabeLO, including the service API and the interfaces required to extend the conversion to a new format, are also provided. To evaluate the effectiveness and efficiency of this approach this paper reports on two actual uses of BabeLO: to relocate exercises to a different repository; and to use an evaluation engine in a network of heterogeneous systems.

Estimation of 3D shapes using active surface models

This paper addresses the estimation of surfaces from a set of 3D points using the unified framework described in [1]. This framework proposes the use of competitive learning for curve estimation, i.e., a set of points is defined on a deformable curve and they all compete to represent the available data. This paper extends the use of the unified framework to surface estimation. It o shown that competitive learning performes better than snakes, improving the model performance in the presence of concavities and allowing to desciminate close surfaces. The proposed model is evaluated in this paper using syntheticdata and medical images (MRI and ultrasound images).

Anàlisi de l'estructura d'aprenentatge en l'ensenyament de l'educació fí­sica en l'educació obligatòria

En el present treball de recerca s'analitza l'estructura d'aprenentatge que els mestres utilitzen en diverses classes d'educació física en l'educació obligatòria. El treball s'organitza en dues parts, una primera part on s'explica què s'entén per educació física i estructura d'aprenentatge i on es relacionen els objectius generals de l'àrea amb els tipus d'estructura d'aprenentatge, individualista, competitiva o cooperativa, més adient per tal d'aconseguir-los. I una segona part on es dissenyen els instruments per a l'anàlisi de l'estructura i l'aprenentatge i s'utilitzen per l'observació de les classes de cinc mestres de cinc escoles diferents de la comarca d'Osona. En les conclusions del treball s'analitza la idoneïtat dels instruments analitzats i es constata la gran utilització de l'estructura d'aprenentatge competitiva en les classes observades.

BIO-INSPIRED COMPUTATIONAL TECHNIQUES APPLIED TO THE CLUSTERING AND VISUALIZATION OF SPATIO-TEMPORAL GEOSPATIAL DATA

The coverage and volume of geo-referenced datasets are extensive and incessantly¦growing. The systematic capture of geo-referenced information generates large volumes¦of spatio-temporal data to be analyzed. Clustering and visualization play a key¦role in the exploratory data analysis and the extraction of knowledge embedded in¦these data. However, new challenges in visualization and clustering are posed when¦dealing with the special characteristics of this data. For instance, its complex structures,¦large quantity of samples, variables involved in a temporal context, high dimensionality¦and large variability in cluster shapes.¦The central aim of my thesis is to propose new algorithms and methodologies for¦clustering and visualization, in order to assist the knowledge extraction from spatiotemporal¦geo-referenced data, thus improving making decision processes.¦I present two original algorithms, one for clustering: the Fuzzy Growing Hierarchical¦Self-Organizing Networks (FGHSON), and the second for exploratory visual data analysis:¦the Tree-structured Self-organizing Maps Component Planes. In addition, I present¦methodologies that combined with FGHSON and the Tree-structured SOM Component¦Planes allow the integration of space and time seamlessly and simultaneously in¦order to extract knowledge embedded in a temporal context.¦The originality of the FGHSON lies in its capability to reflect the underlying structure¦of a dataset in a hierarchical fuzzy way. A hierarchical fuzzy representation of¦clusters is crucial when data include complex structures with large variability of cluster¦shapes, variances, densities and number of clusters. The most important characteristics¦of the FGHSON include: (1) It does not require an a-priori setup of the number¦of clusters. (2) The algorithm executes several self-organizing processes in parallel.¦Hence, when dealing with large datasets the processes can be distributed reducing the¦computational cost. (3) Only three parameters are necessary to set up the algorithm.¦In the case of the Tree-structured SOM Component Planes, the novelty of this algorithm¦lies in its ability to create a structure that allows the visual exploratory data analysis¦of large high-dimensional datasets. This algorithm creates a hierarchical structure¦of Self-Organizing Map Component Planes, arranging similar variables' projections in¦the same branches of the tree. Hence, similarities on variables' behavior can be easily¦detected (e.g. local correlations, maximal and minimal values and outliers).¦Both FGHSON and the Tree-structured SOM Component Planes were applied in¦several agroecological problems proving to be very efficient in the exploratory analysis¦and clustering of spatio-temporal datasets.¦In this thesis I also tested three soft competitive learning algorithms. Two of them¦well-known non supervised soft competitive algorithms, namely the Self-Organizing¦Maps (SOMs) and the Growing Hierarchical Self-Organizing Maps (GHSOMs); and the¦third was our original contribution, the FGHSON. Although the algorithms presented¦here have been used in several areas, to my knowledge there is not any work applying¦and comparing the performance of those techniques when dealing with spatiotemporal¦geospatial data, as it is presented in this thesis.¦I propose original methodologies to explore spatio-temporal geo-referenced datasets¦through time. Our approach uses time windows to capture temporal similarities and¦variations by using the FGHSON clustering algorithm. The developed methodologies¦are used in two case studies. In the first, the objective was to find similar agroecozones¦through time and in the second one it was to find similar environmental patterns¦shifted in time.¦Several results presented in this thesis have led to new contributions to agroecological¦knowledge, for instance, in sugar cane, and blackberry production.¦Finally, in the framework of this thesis we developed several software tools: (1)¦a Matlab toolbox that implements the FGHSON algorithm, and (2) a program called¦BIS (Bio-inspired Identification of Similar agroecozones) an interactive graphical user¦interface tool which integrates the FGHSON algorithm with Google Earth in order to¦show zones with similar agroecological characteristics.

Emergence of oriented circuits driven by synaptic pruning associated with spike-timing-dependent plasticity (STDP)

ABSTRACT: Massive synaptic pruning following over-growth is a general feature of mammalian brain maturation. Pruning starts near time of birth and is completed by time of sexual maturation. Trigger signals able to induce synaptic pruning could be related to dynamic functions that depend on the timing of action potentials. Spike-timing-dependent synaptic plasticity (STDP) is a change in the synaptic strength based on the ordering of pre- and postsynaptic spikes. The relation between synaptic efficacy and synaptic pruning suggests that the weak synapses may be modified and removed through competitive "learning" rules. This plasticity rule might produce the strengthening of the connections among neurons that belong to cell assemblies characterized by recurrent patterns of firing. Conversely, the connections that are not recurrently activated might decrease in efficiency and eventually be eliminated. The main goal of our study is to determine whether or not, and under which conditions, such cell assemblies may emerge out of a locally connected random network of integrate-and-fire units distributed on a 2D lattice receiving background noise and content-related input organized in both temporal and spatial dimensions. The originality of our study stands on the relatively large size of the network, 10,000 units, the duration of the experiment, 10E6 time units (one time unit corresponding to the duration of a spike), and the application of an original bio-inspired STDP modification rule compatible with hardware implementation. A first batch of experiments was performed to test that the randomly generated connectivity and the STDP-driven pruning did not show any spurious bias in absence of stimulation. Among other things, a scale factor was approximated to compensate for the network size on the ac¬tivity. Networks were then stimulated with the spatiotemporal patterns. The analysis of the connections remaining at the end of the simulations, as well as the analysis of the time series resulting from the interconnected units activity, suggest that feed-forward circuits emerge from the initially randomly connected networks by pruning. RESUME: L'élagage massif des synapses après une croissance excessive est une phase normale de la ma¬turation du cerveau des mammifères. L'élagage commence peu avant la naissance et est complété avant l'âge de la maturité sexuelle. Les facteurs déclenchants capables d'induire l'élagage des synapses pourraient être liés à des processus dynamiques qui dépendent de la temporalité rela¬tive des potentiels d'actions. La plasticité synaptique à modulation temporelle relative (STDP) correspond à un changement de la force synaptique basé sur l'ordre des décharges pré- et post- synaptiques. La relation entre l'efficacité synaptique et l'élagage des synapses suggère que les synapses les plus faibles pourraient être modifiées et retirées au moyen d'une règle "d'appren¬tissage" faisant intervenir une compétition. Cette règle de plasticité pourrait produire le ren¬forcement des connexions parmi les neurones qui appartiennent à une assemblée de cellules caractérisée par des motifs de décharge récurrents. A l'inverse, les connexions qui ne sont pas activées de façon récurrente pourraient voir leur efficacité diminuée et être finalement éliminées. Le but principal de notre travail est de déterminer s'il serait possible, et dans quelles conditions, que de telles assemblées de cellules émergent d'un réseau d'unités integrate-and¬-fire connectées aléatoirement et distribuées à la surface d'une grille bidimensionnelle recevant à la fois du bruit et des entrées organisées dans les dimensions temporelle et spatiale. L'originalité de notre étude tient dans la taille relativement grande du réseau, 10'000 unités, dans la durée des simulations, 1 million d'unités de temps (une unité de temps correspondant à une milliseconde), et dans l'utilisation d'une règle STDP originale compatible avec une implémentation matérielle. Une première série d'expériences a été effectuée pour tester que la connectivité produite aléatoirement et que l'élagage dirigé par STDP ne produisaient pas de biais en absence de stimu¬lation extérieure. Entre autres choses, un facteur d'échelle a pu être approximé pour compenser l'effet de la variation de la taille du réseau sur son activité. Les réseaux ont ensuite été stimulés avec des motifs spatiotemporels. L'analyse des connexions se maintenant à la fin des simulations, ainsi que l'analyse des séries temporelles résultantes de l'activité des neurones, suggèrent que des circuits feed-forward émergent par l'élagage des réseaux initialement connectés au hasard.

Emprego de redes neurais artificiais supervisionadas e não supervisionadas no estudo de parâmetros reológicos de excipientes farmacêuticos sólidos

In this paper artificial neural network (ANN) based on supervised and unsupervised algorithms were investigated for use in the study of rheological parameters of solid pharmaceutical excipients, in order to develop computational tools for manufacturing solid dosage forms. Among four supervised neural networks investigated, the best learning performance was achieved by a feedfoward multilayer perceptron whose architectures was composed by eight neurons in the input layer, sixteen neurons in the hidden layer and one neuron in the output layer. Learning and predictive performance relative to repose angle was poor while to Carr index and Hausner ratio (CI and HR, respectively) showed very good fitting capacity and learning, therefore HR and CI were considered suitable descriptors for the next stage of development of supervised ANNs. Clustering capacity was evaluated for five unsupervised strategies. Network based on purely unsupervised competitive strategies, classic "Winner-Take-All", "Frequency-Sensitive Competitive Learning" and "Rival-Penalize Competitive Learning" (WTA, FSCL and RPCL, respectively) were able to perform clustering from database, however this classification was very poor, showing severe classification errors by grouping data with conflicting properties into the same cluster or even the same neuron. On the other hand it could not be established what was the criteria adopted by the neural network for those clustering. Self-Organizing Maps (SOM) and Neural Gas (NG) networks showed better clustering capacity. Both have recognized the two major groupings of data corresponding to lactose (LAC) and cellulose (CEL). However, SOM showed some errors in classify data from minority excipients, magnesium stearate (EMG) , talc (TLC) and attapulgite (ATP). NG network in turn performed a very consistent classification of data and solve the misclassification of SOM, being the most appropriate network for classifying data of the study. The use of NG network in pharmaceutical technology was still unpublished. NG therefore has great potential for use in the development of software for use in automated classification systems of pharmaceutical powders and as a new tool for mining and clustering data in drug development