Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

A behavior-based scheme using reinforcement learning for autonomous underwater vehicles

This paper presents a hybrid behavior-based scheme using reinforcement learning for high-level control of autonomous underwater vehicles (AUVs). Two main features of the presented approach are hybrid behavior coordination and semi on-line neural-Q_learning (SONQL). Hybrid behavior coordination takes advantages of robustness and modularity in the competitive approach as well as efficient trajectories in the cooperative approach. SONQL, a new continuous approach of the Q_learning algorithm with a multilayer neural network is used to learn behavior state/action mapping online. Experimental results show the feasibility of the presented approach for AUVs

Adaption of Courses and Learning Environment to the User Context in dotLRN

The explosive growth of Internet during the last years has been reflected in the ever-increasing amount of the diversity and heterogeneity of user preferences, types and features of devices and access networks. Usually the heterogeneity in the context of the users which request Web contents is not taken into account by the servers that deliver them implying that these contents will not always suit their needs. In the particular case of e-learning platforms this issue is especially critical due to the fact that it puts at stake the knowledge acquired by their users. In the following paper we present a system that aims to provide the dotLRN e-learning platform with the capability to adapt to its users context. By integrating dotLRN with a multi-agent hypermedia system, online courses being undertaken by students as well as their learning environment are adapted in real time

Adaptive intelligent agent approach to guide the web navigation on the PLAN-G distance learning platform

Hypermedia systems based on the Web for open distance education are becoming increasingly popular as tools for user-driven access learning information. Adaptive hypermedia is a new direction in research within the area of user-adaptive systems, to increase its functionality by making it personalized [Eklu 961. This paper sketches a general agents architecture to include navigational adaptability and user-friendly processes which would guide and accompany the student during hislher learning on the PLAN-G hypermedia system (New Generation Telematics Platform to Support Open and Distance Learning), with the aid of computer networks and specifically WWW technology [Marz 98-1] [Marz 98-2]. The PLAN-G actual prototype is successfully used with some informatics courses (the current version has no agents yet). The propased multi-agent system, contains two different types of adaptive autonomous software agents: Personal Digital Agents {Interface), to interacl directly with the student when necessary; and Information Agents (Intermediaries), to filtrate and discover information to learn and to adapt navigation space to a specific student

Social Networking Sites as Technology Enhanced Learning Communities towards autonomous language learning

The following contribution pretends to cope with the demands of a globalised, post-modern environment through the design and implementation of an online international project where an SNS is used in order to join English as Second Language (ESL) students from different parts of the world. The design of the project appears around the implementation of the Bologna process in the Faculty of Education from the University of Girona where the basic prerequisite of all students to acquire English at the level B1 of the Common European Portfolio makes English a compulsory competence for communication among its higher education candidates in order to develop in the world. Together with the University of Girona, there is the International Educational and Resources Network (iEARN) which promotes the participation of schools around the world in online international projects

Facebook & BlackBoard: comparative view of learning environments

For several years, online educational tools such as Blackboard have been used by Universities to foster collaborative learning in an online setting. Such tools tend to be implemented in a top-down fashion, with the institution providing the tool to the students and instructing them to use it. Recently, however, a more informal, bottom up approach is increasingly being employed by the students themselves in the form of social networks such as Facebook. With over 9,000 registered Facebook users at the beginning of this study, rising to over 12,000 at the University of Reading alone, Facebook is becoming the de facto social network of choice for higher education students in the UK, and there was increasing anecdotal evidence that students were actively learning via Facebook rather than through BlackBoard. To test the validity of these anecdotes, a questionnaire was sent to students, asking them about their learning experiences via BlackBoard and Facebook. The results show that students are making use of the tools available to them even when there is no formal academic content, and that increased use of a social networking tool is correlated with a reported increase in learning as a result of that use.

Modeling the user knowledge by belief networks

This paper describes the user modeling component of EPIAIM, a consultation system for data analysis in epidemiology. The component is aimed at representing knowledge of concepts in the domain, so that their explanations can be adapted to user needs. The first part of the paper describes two studies aimed at analysing user requirements. The first one is a questionnaire study which examines the respondents' familiarity with concepts. The second one is an analysis of concept descriptions in textbooks and from expert epidemiologists, which examines how discourse strategies are tailored to the level of experience of the expected audience. The second part of the paper describes how the results of these studies have been used to design the user modeling component of EPIAIM. This module works in a two-step approach. In the first step, a few trigger questions allow the activation of a stereotype that includes a "body" and an "inference component". The body is the representation of the body of knowledge that a class of users is expected to know, along with the probability that the knowledge is known. In the inference component, the learning process of concepts is represented as a belief network. Hence, in the second step the belief network is used to refine the initial default information in the stereotype's body. This is done by asking a few questions on those concepts where it is uncertain whether or not they are known to the user, and propagating this new evidence to revise the whole situation. The system has been implemented on a workstation under UNIX. An example of functioning is presented, and advantages and limitations of the approach are discussed.

Improved SOM learning using simulated annealing

Self-Organizing Map (SOM) algorithm has been extensively used for analysis and classification problems. For this kind of problems, datasets become more and more large and it is necessary to speed up the SOM learning. In this paper we present an application of the Simulated Annealing (SA) procedure to the SOM learning algorithm. The goal of the algorithm is to obtain fast learning and better performance in terms of matching of input data and regularity of the obtained map. An advantage of the proposed technique is that it preserves the simplicity of the basic algorithm. Several tests, carried out on different large datasets, demonstrate the effectiveness of the proposed algorithm in comparison with the original SOM and with some of its modification introduced to speed-up the learning.

Adaptive routing in active networks

New conceptual ideas on network architectures have been proposed in the recent past. Current store-andforward routers are replaced by active intermediate systems, which are able to perform computations on transient packets, in a way that results very helpful for developing and deploying new protocols in a short time. This paper introduces a new routing algorithm, based on a congestion metric, and inspired by the behavior of ants in nature. The use of the Active Networks paradigm associated with a cooperative learning environment produces a robust, decentralized algorithm capable of adapting quickly to changing conditions.

A hierarchical Bayesian model for predicting the functional consequences of amino-acid polymorphisms

Genetic polymorphisms in deoxyribonucleic acid coding regions may have a phenotypic effect on the carrier, e.g. by influencing susceptibility to disease. Detection of deleterious mutations via association studies is hampered by the large number of candidate sites; therefore methods are needed to narrow down the search to the most promising sites. For this, a possible approach is to use structural and sequence-based information of the encoded protein to predict whether a mutation at a particular site is likely to disrupt the functionality of the protein itself. We propose a hierarchical Bayesian multivariate adaptive regression spline (BMARS) model for supervised learning in this context and assess its predictive performance by using data from mutagenesis experiments on lac repressor and lysozyme proteins. In these experiments, about 12 amino-acid substitutions were performed at each native amino-acid position and the effect on protein functionality was assessed. The training data thus consist of repeated observations at each position, which the hierarchical framework is needed to account for. The model is trained on the lac repressor data and tested on the lysozyme mutations and vice versa. In particular, we show that the hierarchical BMARS model, by allowing for the clustered nature of the data, yields lower out-of-sample misclassification rates compared with both a BMARS and a frequen-tist MARS model, a support vector machine classifier and an optimally pruned classification tree.

Learning across business sectors: Knowledge sharing between aerospace and construction

This report addresses the extent that managerial practices can be shared between the aerospace and construction sectors. Current recipes for learning from other industries tend to be oversimplistic and often fail to recognise the embedded and contextual nature of managerial knowledge. Knowledge sharing between business sectors is best understood as an essential source of innovation. The process of comparison challenges assumptions and better equips managers to cope with future change. Comparisons between the aerospace and construction sectors are especially useful because they are so different. The two sectors differ hugely in terms of their institutional context, structure and technological intensity. The aerospace sector has experienced extensive consolidation and is dominated by a small number of global companies. Aerospace companies operate within complex networks of global interdependency such that collaborative working is a commercial imperative. In contrast, the construction sector remains highly fragmented and is characterised by a continued reliance on small firms. The vast majority of construction firms compete within localised markets that are too often characterised by opportunistic behaviour. Comparing construction to aerospace highlights the unique characteristics of both sectors and helps explain how managerial practices are mediated by context. Detailed comparisons between the two sectors are made in a range of areas and guidance is provided for the implementation of knowledge sharing strategies within and across organisations. The commonly accepted notion of ‘best practice’ is exposed as a myth. Indeed, universal models of best practice can be detrimental to performance by deflecting from the need to adapt continuously to changing circumstances. Competitiveness in the construction sector too often rests on efficiency in managing contracts, with a particular emphasis on the allocation of risk. Innovation in construction tends to be problem-driven and is rarely shared from project to project. In aerospace, the dominant model of competitiveness means that firms have little choice other than to invest in continuous innovation, despite difficult trading conditions. Research and development (R&D) expenditure in aerospace continues to rise as a percentage of turnovers. A sustained capacity for innovation within the aerospace sector depends crucially upon stability and continuity of work. In the construction sector, the emergence of the ‘hollowed-out’ firm has undermined the industry’s capacity for innovation. Integrated procurement contexts such as prime contracting in construction potentially provide a more supportive climate for an innovation-based model of competitiveness. However, investment in new ways of working depends upon a shift in thinking not only amongst construction contractors, but also amongst the industry’s major clients.

Emergent discourses of construction competitiveness: localized learning and embeddedness

Research is described that sought to understand how senior managers within regional contracting firms conceptualize and enact competitiveness. Existing formal discourses of construction competitiveness include the discourse of 'best practice' and the various theories of competitiveness as routinely mobilized within the academic literature. Such discourses consistently underplay the influence of contextual factors in shaping how competitiveness is enacted. An alternative discourse of competitiveness is outlined based on the concepts of localized learning and embeddedness. Two case studies of regional construction firms provide new insights into the emergent discourses of construction competitiveness. The empirical findings resonate strongly with the concepts of localized learning and embeddedness. The case studies illustrate the importance of de-centralized structures which enable multiple business units to become embedded within localized markets. A significant degree of autonomy is essential to facilitate localized entrepreneurial behaviour. In essence, sustained competitiveness was found to depend upon the extent to which de-centralized business units enact ongoing processes of localized learning. Once local business units have become embedded within localized markets the essential challenge is how to encourage continued entrepreneurial behaviour while maintaining a degree of centralized control and coordination. Of key importance is the recognition that the capabilities that make companies competitive transcend organizational boundaries such that they become situated within complex networks of relational ties.

Mining gene networks with application to GAW15 problem 1

The genetic analysis workshop 15 (GAW15) problem 1 contained baseline expression levels of 8793 genes in immortalised B cells from 194 individuals in 14 Centre d’Etude du Polymorphisme Humane (CEPH) Utah pedigrees. Previous analysis of the data showed linkage and association and evidence of substantial individual variations. In particular, correlation was examined on expression levels of 31 genes and 25 target genes corresponding to two master regulatory regions. In this analysis, we apply Bayesian network analysis to gain further insight into these findings. We identify strong dependences and therefore provide additional insight into the underlying relationships between the genes involved. More generally, the approach is expected to be applicable for integrated analysis of genes on biological pathways.

Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.