Automating Exersises Validation in e-Learning Environments

E-learning is supposing an innovation in teaching, raising from the development of new technologies. It is based in a set of educational resources, including, among others, multimedia or interactive contents accessible through Internet or Intranet networks. A whole spectrum of tools and services support e-learning, some of them include auto-evaluation and automated correction of test-like exercises, however, this sort of exercises are very constrained because of its nature: fixed contents and correct answers suppose a limit in the way teachers may evaluation students. In this paper we propose a new engine that allows validating complex exercises in the area of Data Structures and Algorithms. Correct solutions to exercises do not rely only in how good the execution of the code is, or if the results are same as expected. A set of criteria on algorithm complexity or correctness in the use of the data structures are required. The engine presented in this work covers a wide set of exercises with these characteristics allowing teachers to establish the set of requirements for a solution, and students to obtain a measure on the quality of their solution in the same terms that are later required for exams.

A Statistical Convergence Aplication for the Hopfield Networks

When Recurrent Neural Networks (RNN) are going to be used as Pattern Recognition systems, the problem to be considered is how to impose prescribed prototype vectors ξ^1,ξ^2,...,ξ^p as fixed points. The synaptic matrix W should be interpreted as a sort of sign correlation matrix of the prototypes, In the classical approach. The weak point in this approach, comes from the fact that it does not have the appropriate tools to deal efficiently with the correlation between the state vectors and the prototype vectors The capacity of the net is very poor because one can only know if one given vector is adequately correlated with the prototypes or not and we are not able to know what its exact correlation degree. The interest of our approach lies precisely in the fact that it provides these tools. In this paper, a geometrical vision of the dynamic of states is explained. A fixed point is viewed as a point in the Euclidean plane R2. The retrieving procedure is analyzed trough statistical frequency distribution of the prototypes. The capacity of the net is improved and the spurious states are reduced. In order to clarify and corroborate the theoretical results, together with the formal theory, an application is presented

Growing Neural Networks Using Nonconventional Activation Functions

In the paper, an ontogenic artificial neural network (ANNs) is proposed. The network uses orthogonal activation functions that allow significant reducing of computational complexity. Another advantage is numerical stability, because the system of activation functions is linearly independent by definition. A learning procedure for proposed ANN with guaranteed convergence to the global minimum of error function in the parameter space is developed. An algorithm for structure network structure adaptation is proposed. The algorithm allows adding or deleting a node in real-time without retraining of the network. Simulation results confirm the efficiency of the proposed approach.

Filtered Networks of Evolutionary Processors

* Supported by INTAS 00-626 and TIC 2003-09319-c03-03.

A New Approach for Eliminating the Spurious States in Recurrent Neural Networks

As is well known, the Convergence Theorem for the Recurrent Neural Networks, is based in Lyapunov ́s second method, which states that associated to any one given net state, there always exist a real number, in other words an element of the one dimensional Euclidean Space R, in such a way that when the state of the net changes then its associated real number decreases. In this paper we will introduce the two dimensional Euclidean space R2, as the space associated to the net, and we will define a pair of real numbers ( x, y ) , associated to any one given state of the net. We will prove that when the net change its state, then the product x ⋅ y will decrease. All the states whose projection over the energy field are placed on the same hyperbolic surface, will be considered as points with the same energy level. On the other hand we will prove that if the states are classified attended to their distances to the zero vector, only one pattern in each one of the different classes may be at the same energy level. The retrieving procedure is analyzed trough the projection of the states on that plane. The geometrical properties of the synaptic matrix W may be used for classifying the n-dimensional state- vector space in n classes. A pattern to be recognized is seen as a point belonging to one of these classes, and depending on the class the pattern to be retrieved belongs, different weight parameters are used. The capacity of the net is improved and the spurious states are reduced. In order to clarify and corroborate the theoretical results, together with the formal theory, an application is presented.

Neural Networks: A Diagnostic Tool for Gastric Electrical Uncoupling?

Neural Networks have been successfully employed in different biomedical settings. They have been useful for feature extractions from images and biomedical data in a variety of diagnostic applications. In this paper, they are applied as a diagnostic tool for classifying different levels of gastric electrical uncoupling in controlled acute experiments on dogs. Data was collected from 16 dogs using six bipolar electrodes inserted into the serosa of the antral wall. Each dog underwent three recordings under different conditions: (1) basal state, (2) mild surgically-induced uncoupling, and (3) severe surgically-induced uncoupling. For each condition half-hour recordings were made. The neural network was implemented according to the Learning Vector Quantization model. This is a supervised learning model of the Kohonen Self-Organizing Maps. Majority of the recordings collected from the dogs were used for network training. Remaining recordings served as a testing tool to examine the validity of the training procedure. Approximately 90% of the dogs from the neural network training set were classified properly. However, only 31% of the dogs not included in the training process were accurately diagnosed. The poor neural-network based diagnosis of recordings that did not participate in the training process might have been caused by inappropriate representation of input data. Previous research has suggested characterizing signals according to certain features of the recorded data. This method, if employed, would reduce the noise and possibly improve the diagnostic abilities of the neural network.

Data Mining for Browsing Patterns in Weblog Data by Art Neural Networks

Categorising visitors based on their interaction with a website is a key problem in Web content usage. The clickstreams generated by various users often follow distinct patterns, the knowledge of which may help in providing customised content. This paper proposes an approach to clustering weblog data, based on ART2 neural networks. Due to the characteristics of the ART2 neural network model, the proposed approach can be used for unsupervised and self-learning data mining, which makes it adaptable to dynamically changing websites.

String Measure Applied to String Self-Organizing Maps and Networks of Evolutionary Processors

* Supported by projects CCG08-UAM TIC-4425-2009 and TEC2007-68065-C03-02

The Cascade Neo-Fuzzy Architecture and its Online Learning Algorithm

In the paper learning algorithm for adjusting weight coefficients of the Cascade Neo-Fuzzy Neural Network (CNFNN) in sequential mode is introduced. Concerned architecture has the similar structure with the Cascade-Correlation Learning Architecture proposed by S.E. Fahlman and C. Lebiere, but differs from it in type of artificial neurons. CNFNN consists of neo-fuzzy neurons, which can be adjusted using high-speed linear learning procedures. Proposed CNFNN is characterized by high learning rate, low size of learning sample and its operations can be described by fuzzy linguistic “if-then” rules providing “transparency” of received results, as compared with conventional neural networks. Using of online learning algorithm allows to process input data sequentially in real time mode.

Self-organising zooms for decentralised redundancy management in visual sensor networks

When visual sensor networks are composed of cameras which can adjust the zoom factor of their own lens, one must determine the optimal zoom levels for the cameras, for a given task. This gives rise to an important trade-off between the overlap of the different cameras’ fields of view, providing redundancy, and image quality. In an object tracking task, having multiple cameras observe the same area allows for quicker recovery, when a camera fails. In contrast having narrow zooms allow for a higher pixel count on regions of interest, leading to increased tracking confidence. In this paper we propose an approach for the self-organisation of redundancy in a distributed visual sensor network, based on decentralised multi-objective online learning using only local information to approximate the global state. We explore the impact of different zoom levels on these trade-offs, when tasking omnidirectional cameras, having perfect 360-degree view, with keeping track of a varying number of moving objects. We further show how employing decentralised reinforcement learning enables zoom configurations to be achieved dynamically at runtime according to an operator’s preference for maximising either the proportion of objects tracked, confidence associated with tracking, or redundancy in expectation of camera failure. We show that explicitly taking account of the level of overlap, even based only on local knowledge, improves resilience when cameras fail. Our results illustrate the trade-off between maintaining high confidence and object coverage, and maintaining redundancy, in anticipation of future failure. Our approach provides a fully tunable decentralised method for the self-organisation of redundancy in a changing environment, according to an operator’s preferences.

Static, dynamic, and adaptive heterogeneity in distributed smart camera networks

We study heterogeneity among nodes in self-organizing smart camera networks, which use strategies based on social and economic knowledge to target communication activity efficiently. We compare homogeneous configurations, when cameras use the same strategy, with heterogeneous configurations, when cameras use different strategies. Our first contribution is to establish that static heterogeneity leads to new outcomes that are more efficient than those possible with homogeneity. Next, two forms of dynamic heterogeneity are investigated: nonadaptive mixed strategies and adaptive strategies, which learn online. Our second contribution is to show that mixed strategies offer Pareto efficiency consistently comparable with the most efficient static heterogeneous configurations. Since the particular configuration required for high Pareto efficiency in a scenario will not be known in advance, our third contribution is to show how decentralized online learning can lead to more efficient outcomes than the homogeneous case. In some cases, outcomes from online learning were more efficient than all other evaluated configuration types. Our fourth contribution is to show that online learning typically leads to outcomes more evenly spread over the objective space. Our results provide insight into the relationship between static, dynamic, and adaptive heterogeneity, suggesting that all have a key role in achieving efficient self-organization.

Counting on use of technology to enhance learning

In global policy documents, the language of Technology-Enhanced Learning (TEL) now firmly structures a perception of educational technology which ‘subsumes’ terms like Networked Learning and e-Learning. Embedded in these three words though is a deterministic, economic assumption that technology has now enhanced learning, and will continue to do so. In a market-driven, capitalist society this is a ‘trouble free’, economically focused discourse which suggests there is no need for further debate about what the use of technology achieves in learning. Yet this raises a problem too: if technology achieves goals for human beings, then in education we are now simply counting on ‘use of technology’ to enhance learning. This closes the door on a necessary and ongoing critical pedagogical conversation that reminds us it is people that design learning, not technology. Furthermore, such discourse provides a vehicle for those with either strong hierarchical, or neoliberal agendas to make simplified claims politically, in the name of technology. This chapter is a reflection on our use of language in the educational technology community through a corpus-based Critical Discourse Analysis (CDA). In analytical examples that are ‘loaded’ with economic expectation, we can notice how the policy discourse of TEL narrows conversational space for learning so that people may struggle to recognise their own subjective being in this language. Through the lens of Lieras’s externality, desubjectivisation and closure (Lieras, 1996) we might examine possible effects of this discourse and seek a more emancipatory approach. A return to discussing Networked Learning is suggested, as a first step towards a more multi-directional conversation than TEL, that acknowledges the interrelatedness of technology, language and learning in people’s practice. Secondly, a reconsideration of how we write policy for educational technology is recommended, with a critical focus on how people learn, rather than on what technology is assumed to enhance.

Organisational learning, climate change and the tragedy of the commons in China

This paper ends with a brief discussion of climate change and suggests that a practical solution would be to transfer much of the current air, sea and long-haul trucking of intercontinental freight between China and Europe (and the USA) to maglev systems. First we review the potential of Asian knowledge management and organisational learning and contrast this against Western precepts finding that there seems to be little incentive to 'look after one's fellows' in China (and perhaps across Asia) outside of tight personal guanxi networks. This is likely to be the case in the intense production regions of China where little time is allowed for 'organisational learning' by the staff and there is little incentive to initiate 'knowledge management' by senior managers. Thus the 'tragedy of the commons' will be enacted by individuals, township, and provincial leaders upwards to top ministers - no one will care for the climate or pollution, only for their own group and their wealth creation prospects. Copyright © 2011 Inderscience Enterprises Ltd.

Kis- és középvállalatok innovációs tevékenysége a válság idején – hálózatok szerepe (Innovation of small and medium-sized enterprises in times of crises – The role of networks)

A hálózati megközelítés alapján a vállalatok nem izoláltan működő szervezetek. A kis- és középvállalkozások számára a hálózatok, a partnerkapcsolatok jelentős támogatást képesek biztosítani a növekedés, a tanulás és az innovációs tevékenység során. A szerző a hálózati, partneri kapcsolatok szerepét a válság idején vizsgálta, kvalitatív kutatás keretében. A tanulmány fontos megállapítása, hogy nem kizárólag a hálózatban rejlő lehetőségek, hanem a korábban biztos partneri kapcsolatok megszűnése is indukálhat innovációt a válság idején, valamint a biztonság, a tartalék-erőforrások megléte esetén lassabb a piaci reagálás, kevésbé kerül előtérbe a változás, s főként az innovációs tevékenység ______ Based on the network perspective companies are not isolated organizations. Networks and partnerships mean a significant support for SMEs in growth, learning and innovation. The author examines the role of networks and partnerships during the crisis, in a qualitative research. An important result of the paper is that not only the opportunities in networks but also the decomposition of prior secure relationships can induce innovation during the crisis. Moreover in case of safety and slack resources the reaction is slower, change and innovation come to the front less.

Remote learning and laboratory center over Internet and ISDN

Recent advances in telecommunications technologies have transformed the modes of learning and teaching. One potentially vital component in the equation will be Remote Education or Remote Learning, the ability to compress time and space between teachers and students through the judicious application of technology. The purpose of this thesis is to develop a Remote Learning and Laboratory Center over the Internet and ISDN, which provide education and access to resources to those living in remote areas, children in hospitals and traveling families, with audio, video and data.^ Remote Learning and Laboratory Center (RLLC) is not restricted to merely traditional education processes such as universities or colleges, it can be very useful for companies to train their engineers, via networks. This capability will facilitate the best use of scarce, high quality educational resources and will bring equity of services to students as well as will be helpful to the Industries to train their engineers. The RLLC over the Internet and ISDN has been described in details and implemented successfully. For the Remote Laboratory, the experiment procedure has been demonstrated on reprogrammable CPLD design using ISR Kit. ^