Environment mapping for mobile robots navigation using hierarchical neural network and omnivision

Autonomous robots must be able to learn and maintain models of their environments. In this context, the present work considers techniques for the classification and extraction of features from images in joined with artificial neural networks in order to use them in the system of mapping and localization of the mobile robot of Laboratory of Automation and Evolutive Computer (LACE). To do this, the robot uses a sensorial system composed for ultrasound sensors and a catadioptric vision system formed by a camera and a conical mirror. The mapping system is composed by three modules. Two of them will be presented in this paper: the classifier and the characterizer module. The first module uses a hierarchical neural network to do the classification; the second uses techiniques of extraction of attributes of images and recognition of invariant patterns extracted from the places images set. The neural network of the classifier module is structured in two layers, reason and intuition, and is trained to classify each place explored for the robot amongst four predefine classes. The final result of the exploration is the construction of a topological map of the explored environment. Results gotten through the simulation of the both modules of the mapping system will be presented in this paper. © 2008 IEEE.

Image segmentation through combined methods: watershed transform, unsupervised distance learning and normalized cut

Research on image processing has shown that combining segmentation methods may lead to a solid approach to extract semantic information from different sort of images. Within this context, the Normalized Cut (NCut) is usually used as a final partitioning tool for graphs modeled in some chosen method. This work explores the Watershed Transform as a modeling tool, using different criteria of the hierarchical Watershed to convert an image into an adjacency graph. The Watershed is combined with an unsupervised distance learning step that redistributes the graph weights and redefines the Similarity matrix, before the final segmentation step using NCut. Adopting the Berkeley Segmentation Data Set and Benchmark as a background, our goal is to compare the results obtained for this method with previous work to validate its performance.

Parameter recovery for a skew-normal IRT model under a Bayesian approach: hierarchical framework, prior and kernel sensitivity and sample size

Item response theory (IRT) comprises a set of statistical models which are useful in many fields, especially when there is an interest in studying latent variables (or latent traits). Usually such latent traits are assumed to be random variables and a convenient distribution is assigned to them. A very common choice for such a distribution has been the standard normal. Recently, Azevedo et al. [Bayesian inference for a skew-normal IRT model under the centred parameterization, Comput. Stat. Data Anal. 55 (2011), pp. 353-365] proposed a skew-normal distribution under the centred parameterization (SNCP) as had been studied in [R. B. Arellano-Valle and A. Azzalini, The centred parametrization for the multivariate skew-normal distribution, J. Multivariate Anal. 99(7) (2008), pp. 1362-1382], to model the latent trait distribution. This approach allows one to represent any asymmetric behaviour concerning the latent trait distribution. Also, they developed a Metropolis-Hastings within the Gibbs sampling (MHWGS) algorithm based on the density of the SNCP. They showed that the algorithm recovers all parameters properly. Their results indicated that, in the presence of asymmetry, the proposed model and the estimation algorithm perform better than the usual model and estimation methods. Our main goal in this paper is to propose another type of MHWGS algorithm based on a stochastic representation (hierarchical structure) of the SNCP studied in [N. Henze, A probabilistic representation of the skew-normal distribution, Scand. J. Statist. 13 (1986), pp. 271-275]. Our algorithm has only one Metropolis-Hastings step, in opposition to the algorithm developed by Azevedo et al., which has two such steps. This not only makes the implementation easier but also reduces the number of proposal densities to be used, which can be a problem in the implementation of MHWGS algorithms, as can be seen in [R.J. Patz and B.W. Junker, A straightforward approach to Markov Chain Monte Carlo methods for item response models, J. Educ. Behav. Stat. 24(2) (1999), pp. 146-178; R. J. Patz and B. W. Junker, The applications and extensions of MCMC in IRT: Multiple item types, missing data, and rated responses, J. Educ. Behav. Stat. 24(4) (1999), pp. 342-366; A. Gelman, G.O. Roberts, and W.R. Gilks, Efficient Metropolis jumping rules, Bayesian Stat. 5 (1996), pp. 599-607]. Moreover, we consider a modified beta prior (which generalizes the one considered in [3]) and a Jeffreys prior for the asymmetry parameter. Furthermore, we study the sensitivity of such priors as well as the use of different kernel densities for this parameter. Finally, we assess the impact of the number of examinees, number of items and the asymmetry level on the parameter recovery. Results of the simulation study indicated that our approach performed equally as well as that in [3], in terms of parameter recovery, mainly using the Jeffreys prior. Also, they indicated that the asymmetry level has the highest impact on parameter recovery, even though it is relatively small. A real data analysis is considered jointly with the development of model fitting assessment tools. The results are compared with the ones obtained by Azevedo et al. The results indicate that using the hierarchical approach allows us to implement MCMC algorithms more easily, it facilitates diagnosis of the convergence and also it can be very useful to fit more complex skew IRT models.

Learning for well being : Studies using the International Adult Literacy Survey

This thesis is a collection of five independent but closely related studies. The overall purpose is to approach the analysis of learning outcomes from a perspective that combines three major elements, namely lifelonglifewide learning, human capital, and the benefits of learning. The approach is based on an interdisciplinary perspective of the human capital paradigm. It considers the multiple learning contexts that are responsible for the development of embodied potential – including formal, nonformal and informal learning – and the multiple outcomes – including knowledge, skills, economic, social and others– that result from learning. The studies also seek to examine the extent and relative influence of learning in different contexts on the formation of embodied potential and how in turn that affects economic and social well being. The first study combines the three major elements, lifelonglifewide learning, human capital, and the benefits of learning into one common conceptual framework. This study forms a common basis for the four empirical studies that follow. All four empirical studies use data from the International Adult Literacy Survey (IALS) to investigate the relationships among the major elements of the conceptual framework presented in the first study. Study I. A conceptual framework for the analysis of learning outcomes This study brings together some key concepts and theories that are relevant for the analysis of learning outcomes. Many of the concepts and theories have emerged from varied disciplines including economics, educational psychology, cognitive science and sociology, to name only a few. Accordingly, some of the research questions inherent in the framework relate to different disciplinary perspectives. The primary purpose is to create a common basis for formulating and testing hypotheses as well as to interpret the findings in the empirical studies that follow. In particular, the framework facilitates the process of theorizing and hypothesizing on the relationships and processes concerning lifelong learning as well as their antecedents and consequences. Study II. Determinants of literacy proficiency: A lifelong-lifewide learning perspective This study investigates lifelong and lifewide processes of skill formation. In particular, it seeks to estimate the substitutability and complementarity effects of learning in multiple settings over the lifespan on literacy skill formation. This is done by investigating the predictive capacity of major determinants of literacy proficiency that are associated with a variety of learning contexts including school, home, work, community and leisure. An identical structural model based on previous research is fitted to the IALS data for 18 countries. The results show that even after accounting for all factors, education remains the most important predictor of literacy proficiency. In all countries, however, the total effect of education is significantly mediated through further learning occurring at work, at home and in the community. Therefore, the job and other literacy related factors complement education in predicting literacy proficiency. This result points to a virtual cycle of lifelong learning, particularly to how educational attainment influences other learning behaviours throughout life. In addition, results show that home background as measured by parents’ education is also a strong predictor of literacy proficiency, but in many countries this occurs only if a favourable home background is complemented with some post-secondary education. Study III. The effect of literacy proficiency on earnings: An aggregated occupational approach using the Canadian IALS data This study uses data from the Canadian Adult Literacy Survey to estimate the earnings return to literacy skills. The approach adapts a labour segmented view of the labour market by aggregating occupations into seven types, enabling the estimation of the variable impact of literacy proficiency on earnings, both within and between different types of occupations. This is done using Hierarchical Linear Modeling (HLM). The method used to construct the aggregated occupational classification is based on analysis that considers the role of cognitive and other skills in relation to the nature of occupational tasks. Substantial premiums are found to be associated with some occupational types even after adjusting for within occupational differences in individual characteristics such as schooling, literacy proficiency, labour force experience and gender. Average years of schooling and average levels of literacy proficiency at the between level account for over two-thirds of the premiums. Within occupations, there are significant returns to schooling but they vary depending on the type of occupations. In contrast, the within occupational return of literacy proficiency is not necessarily significant. The latter depends on the type of occupation. Study IV: Determinants of economic and social outcomes from a lifewide learning perspective in Canada In this study the relationship between learning in different contexts, which span the lifewide learning dimension, and individual earnings on the one hand and community participation on the other are examined in separate but comparable models. Data from the Canadian Adult Literacy Survey are used to estimate structural models, which correspond closely to the common conceptual framework outlined in Study I. The findings suggest that the relationship between formal education and economic and social outcomes is complex with confounding effects. The results indicate that learning occurring in different contexts and for different reasons leads to different kinds of benefits. The latter finding suggests a potential trade-off between realizing economic and social benefits through learning that are taken for either job-related or personal-interest related reasons. Study V: The effects of learning on economic and social well being: A comparative analysis Using the same structural model as in Study IV, hypotheses are comparatively examined using the International Adult Literacy Survey data for Canada, Denmark, the Netherlands, Norway, the United Kingdom, and the United States. The main finding from Study IV is confirmed for an additional five countries, namely that the effect of initial schooling on well being is more complex than a direct one and it is significantly mediated by subsequent learning. Additionally, findings suggest that people who devote more time to learning for job-related reasons than learning for personal-interest related reasons experience higher levels of economic well being. Moreover, devoting too much time to learning for personal-interest related reasons has a negative effect on earnings except in Denmark. But the more time people devote to learning for personal-interest related reasons tends to contribute to higher levels of social well being. These results again suggest a trade-off in learning for different reasons and in different contexts.

Learning Methods and Algorithms for Semantic Text Classification across Multiple Domains

Information is nowadays a key resource: machine learning and data mining techniques have been developed to extract high-level information from great amounts of data. As most data comes in form of unstructured text in natural languages, research on text mining is currently very active and dealing with practical problems. Among these, text categorization deals with the automatic organization of large quantities of documents in priorly defined taxonomies of topic categories, possibly arranged in large hierarchies. In commonly proposed machine learning approaches, classifiers are automatically trained from pre-labeled documents: they can perform very accurate classification, but often require a consistent training set and notable computational effort. Methods for cross-domain text categorization have been proposed, allowing to leverage a set of labeled documents of one domain to classify those of another one. Most methods use advanced statistical techniques, usually involving tuning of parameters. A first contribution presented here is a method based on nearest centroid classification, where profiles of categories are generated from the known domain and then iteratively adapted to the unknown one. Despite being conceptually simple and having easily tuned parameters, this method achieves state-of-the-art accuracy in most benchmark datasets with fast running times. A second, deeper contribution involves the design of a domain-independent model to distinguish the degree and type of relatedness between arbitrary documents and topics, inferred from the different types of semantic relationships between respective representative words, identified by specific search algorithms. The application of this model is tested on both flat and hierarchical text categorization, where it potentially allows the efficient addition of new categories during classification. Results show that classification accuracy still requires improvements, but models generated from one domain are shown to be effectively able to be reused in a different one.

Spatio-temporal credit assignment in population learning

Learning by reinforcement is important in shaping animal behavior, and in particular in behavioral decision making. Such decision making is likely to involve the integration of many synaptic events in space and time. However, using a single reinforcement signal to modulate synaptic plasticity, as suggested in classical reinforcement learning algorithms, a twofold problem arises. Different synapses will have contributed differently to the behavioral decision, and even for one and the same synapse, releases at different times may have had different effects. Here we present a plasticity rule which solves this spatio-temporal credit assignment problem in a population of spiking neurons. The learning rule is spike-time dependent and maximizes the expected reward by following its stochastic gradient. Synaptic plasticity is modulated not only by the reward, but also by a population feedback signal. While this additional signal solves the spatial component of the problem, the temporal one is solved by means of synaptic eligibility traces. In contrast to temporal difference (TD) based approaches to reinforcement learning, our rule is explicit with regard to the assumed biophysical mechanisms. Neurotransmitter concentrations determine plasticity and learning occurs fully online. Further, it works even if the task to be learned is non-Markovian, i.e. when reinforcement is not determined by the current state of the system but may also depend on past events. The performance of the model is assessed by studying three non-Markovian tasks. In the first task, the reward is delayed beyond the last action with non-related stimuli and actions appearing in between. The second task involves an action sequence which is itself extended in time and reward is only delivered at the last action, as it is the case in any type of board-game. The third task is the inspection game that has been studied in neuroeconomics, where an inspector tries to prevent a worker from shirking. Applying our algorithm to this game yields a learning behavior which is consistent with behavioral data from humans and monkeys, revealing themselves properties of a mixed Nash equilibrium. The examples show that our neuronal implementation of reward based learning copes with delayed and stochastic reward delivery, and also with the learning of mixed strategies in two-opponent games.

Spatio-temporal credit assignment in population learning

Learning by reinforcement is important in shaping animal behavior. But behavioral decision making is likely to involve the integration of many synaptic events in space and time. So in using a single reinforcement signal to modulate synaptic plasticity a twofold problem arises. Different synapses will have contributed differently to the behavioral decision and, even for one and the same synapse, releases at different times may have had different effects. Here we present a plasticity rule which solves this spatio-temporal credit assignment problem in a population of spiking neurons. The learning rule is spike time dependent and maximizes the expected reward by following its stochastic gradient. Synaptic plasticity is modulated not only by the reward but by a population feedback signal as well. While this additional signal solves the spatial component of the problem, the temporal one is solved by means of synaptic eligibility traces. In contrast to temporal difference based approaches to reinforcement learning, our rule is explicit with regard to the assumed biophysical mechanisms. Neurotransmitter concentrations determine plasticity and learning occurs fully online. Further, it works even if the task to be learned is non-Markovian, i.e. when reinforcement is not determined by the current state of the system but may also depend on past events. The performance of the model is assessed by studying three non-Markovian tasks. In the first task the reward is delayed beyond the last action with non-related stimuli and actions appearing in between. The second one involves an action sequence which is itself extended in time and reward is only delivered at the last action, as is the case in any type of board-game. The third is the inspection game that has been studied in neuroeconomics. It only has a mixed Nash equilibrium and exemplifies that the model also copes with stochastic reward delivery and the learning of mixed strategies.

Spike-based decision learning of nash equilibria in two-player games

Humans and animals face decision tasks in an uncertain multi-agent environment where an agent's strategy may change in time due to the co-adaptation of others strategies. The neuronal substrate and the computational algorithms underlying such adaptive decision making, however, is largely unknown. We propose a population coding model of spiking neurons with a policy gradient procedure that successfully acquires optimal strategies for classical game-theoretical tasks. The suggested population reinforcement learning reproduces data from human behavioral experiments for the blackjack and the inspector game. It performs optimally according to a pure (deterministic) and mixed (stochastic) Nash equilibrium, respectively. In contrast, temporal-difference(TD)-learning, covariance-learning, and basic reinforcement learning fail to perform optimally for the stochastic strategy. Spike-based population reinforcement learning, shown to follow the stochastic reward gradient, is therefore a viable candidate to explain automated decision learning of a Nash equilibrium in two-player games.

Gradient estimation in dendritic reinforcement learning

We study synaptic plasticity in a complex neuronal cell model where NMDA-spikes can arise in certain dendritic zones. In the context of reinforcement learning, two kinds of plasticity rules are derived, zone reinforcement (ZR) and cell reinforcement (CR), which both optimize the expected reward by stochastic gradient ascent. For ZR, the synaptic plasticity response to the external reward signal is modulated exclusively by quantities which are local to the NMDA-spike initiation zone in which the synapse is situated. CR, in addition, uses nonlocal feedback from the soma of the cell, provided by mechanisms such as the backpropagating action potential. Simulation results show that, compared to ZR, the use of nonlocal feedback in CR can drastically enhance learning performance. We suggest that the availability of nonlocal feedback for learning is a key advantage of complex neurons over networks of simple point neurons, which have previously been found to be largely equivalent with regard to computational capability.

Eluding oblivion with smart stochastic selection of synaptic updates

The variables involved in the equations that describe realistic synaptic dynamics always vary in a limited range. Their boundedness makes the synapses forgetful, not for the mere passage of time, but because new experiences overwrite old memories. The forgetting rate depends on how many synapses are modified by each new experience: many changes means fast learning and fast forgetting, whereas few changes means slow learning and long memory retention. Reducing the average number of modified synapses can extend the memory span at the price of a reduced amount of information stored when a new experience is memorized. Every trick which allows to slow down the learning process in a smart way can improve the memory performance. We review some of the tricks that allow to elude fast forgetting (oblivion). They are based on the stochastic selection of the synapses whose modifications are actually consolidated following each new experience. In practice only a randomly selected, small fraction of the synapses eligible for an update are actually modified. This allows to acquire the amount of information necessary to retrieve the memory without compromising the retention of old experiences. The fraction of modified synapses can be further reduced in a smart way by changing synapses only when it is really necessary, i.e. when the post-synaptic neuron does not respond as desired. Finally we show that such a stochastic selection emerges naturally from spike driven synaptic dynamics which read noisy pre and post-synaptic neural activities. These activities can actually be generated by a chaotic system.

LEARNING FROM NEAR MISSES IN MEDICATION ERRORS: A BAYESIAN APPROACH

Medical errors originating in health care facilities are a significant source of preventable morbidity, mortality, and healthcare costs. Voluntary error report systems that collect information on the causes and contributing factors of medi- cal errors regardless of the resulting harm may be useful for developing effective harm prevention strategies. Some patient safety experts question the utility of data from errors that did not lead to harm to the patient, also called near misses. A near miss (a.k.a. close call) is an unplanned event that did not result in injury to the patient. Only a fortunate break in the chain of events prevented injury. We use data from a large voluntary reporting system of 836,174 medication errors from 1999 to 2005 to provide evidence that the causes and contributing factors of errors that result in harm are similar to the causes and contributing factors of near misses. We develop Bayesian hierarchical models for estimating the log odds of selecting a given cause (or contributing factor) of error given harm has occurred and the log odds of selecting the same cause given that harm did not occur. The posterior distribution of the correlation between these two vectors of log-odds is used as a measure of the evidence supporting the use of data from near misses and their causes and contributing factors to prevent medical errors. In addition, we identify the causes and contributing factors that have the highest or lowest log-odds ratio of harm versus no harm. These causes and contributing factors should also be a focus in the design of prevention strategies. This paper provides important evidence on the utility of data from near misses, which constitute the vast majority of errors in our data.

Hierarchical Markov Random Fields Applied to Model Soft Tissue Deformations on Graphics Hardware

Many methodologies dealing with prediction or simulation of soft tissue deformations on medical image data require preprocessing of the data in order to produce a different shape representation that complies with standard methodologies, such as mass–spring networks, finite element method s (FEM). On the other hand, methodologies working directly on the image space normally do not take into account mechanical behavior of tissues and tend to lack physics foundations driving soft tissue deformations. This chapter presents a method to simulate soft tissue deformations based on coupled concepts from image analysis and mechanics theory. The proposed methodology is based on a robust stochastic approach that takes into account material properties retrieved directly from the image, concepts from continuum mechanics and FEM. The optimization framework is solved within a hierarchical Markov random field (HMRF) which is implemented on the graphics processor unit (GPU See Graphics processing unit ).

Learning by the Dendritic Prediction of Somatic Spiking

Recent modeling of spike-timing-dependent plasticity indicates that plasticity involves as a third factor a local dendritic potential, besides pre- and postsynaptic firing times. We present a simple compartmental neuron model together with a non-Hebbian, biologically plausible learning rule for dendritic synapses where plasticity is modulated by these three factors. In functional terms, the rule seeks to minimize discrepancies between somatic firings and a local dendritic potential. Such prediction errors can arise in our model from stochastic fluctuations as well as from synaptic input, which directly targets the soma. Depending on the nature of this direct input, our plasticity rule subserves supervised or unsupervised learning. When a reward signal modulates the learning rate, reinforcement learning results. Hence a single plasticity rule supports diverse learning paradigms.

Matching Recall and Storage in Sequence Learning with Spiking Neural Networks

Storing and recalling spiking sequences is a general problem the brain needs to solve. It is, however, unclear what type of biologically plausible learning rule is suited to learn a wide class of spatiotemporal activity patterns in a robust way. Here we consider a recurrent network of stochastic spiking neurons composed of both visible and hidden neurons. We derive a generic learning rule that is matched to the neural dynamics by minimizing an upper bound on the Kullback–Leibler divergence from the target distribution to the model distribution. The derived learning rule is consistent with spike-timing dependent plasticity in that a presynaptic spike preceding a postsynaptic spike elicits potentiation while otherwise depression emerges. Furthermore, the learning rule for synapses that target visible neurons can be matched to the recently proposed voltage-triplet rule. The learning rule for synapses that target hidden neurons is modulated by a global factor, which shares properties with astrocytes and gives rise to testable predictions.

Learning reward timing in cortex through reward dependent expression of synaptic plasticity.

The ability to represent time is an essential component of cognition but its neural basis is unknown. Although extensively studied both behaviorally and electrophysiologically, a general theoretical framework describing the elementary neural mechanisms used by the brain to learn temporal representations is lacking. It is commonly believed that the underlying cellular mechanisms reside in high order cortical regions but recent studies show sustained neural activity in primary sensory cortices that can represent the timing of expected reward. Here, we show that local cortical networks can learn temporal representations through a simple framework predicated on reward dependent expression of synaptic plasticity. We assert that temporal representations are stored in the lateral synaptic connections between neurons and demonstrate that reward-modulated plasticity is sufficient to learn these representations. We implement our model numerically to explain reward-time learning in the primary visual cortex (V1), demonstrate experimental support, and suggest additional experimentally verifiable predictions.