Generalization by Computation Through Memory

Usually, generalization is considered as a function of learning from a set of examples. In present work on the basis of recent neural network assembly memory model (NNAMM), a biologically plausible 'grandmother' model for vision, where each separate memory unit itself can generalize, has been proposed. For such a generalization by computation through memory, analytical formulae and numerical procedure are found to calculate exactly the perfectly learned memory unit's generalization ability. The model's memory has complex hierarchical structure, can be learned from one example by a one-step process, and may be considered as a semi-representational one. A simple binary neural network for bell-shaped tuning is described.

ROC Curves within the Framework of Neural Network Assembly Memory Model: Some Analytic Results

On the basis of convolutional (Hamming) version of recent Neural Network Assembly Memory Model (NNAMM) for intact two-layer autoassociative Hopfield network optimal receiver operating characteristics (ROCs) have been derived analytically. A method of taking into account explicitly a priori probabilities of alternative hypotheses on the structure of information initiating memory trace retrieval and modified ROCs (mROCs, a posteriori probabilities of correct recall vs. false alarm probability) are introduced. The comparison of empirical and calculated ROCs (or mROCs) demonstrates that they coincide quantitatively and in this way intensities of cues used in appropriate experiments may be estimated. It has been found that basic ROC properties which are one of experimental findings underpinning dual-process models of recognition memory can be explained within our one-factor NNAMM.

Non-Linear Network-Flow Model of Lukasiewicz’s Multivalue Logic

The paper presents a new network-flow interpretation of Łukasiewicz’s logic based on models with an increased effectiveness. The obtained results show that the presented network-flow models principally may work for multivalue logics with more than three states of the variables i.e. with a finite set of states in the interval from 0 to 1. The described models give the opportunity to formulate various logical functions. If the results from a given model that are contained in the obtained values of the arc flow functions are used as input data for other models then it is possible in Łukasiewicz’s logic to interpret successfully other sophisticated logical structures. The obtained models allow a research of Łukasiewicz’s logic with specific effective methods of the network-flow programming. It is possible successfully to use the specific peculiarities and the results pertaining to the function ‘traffic capacity of the network arcs’. Based on the introduced network-flow approach it is possible to interpret other multivalue logics – of E.Post, of L.Brauer, of Kolmogorov, etc.

Primary and Secondary Empirical Values in Network Redimensioning

A model of an overall telecommunication network with virtual circuits switching, in stationary state, with Bernoulli-Poisson-Pascal (BPP) input flow, repeated calls, limited number of homogeneous terminals and 8 types of losses is considered. One of the main problems of network redimensioning is estimation of the traffic offered in the network because it reflects on finding of necessary number of equivalent switching lines on the basis of the consideration of detailed users behavior and target Quality of Service (QoS). The aim of this paper is to find a new solution of Network Redimensioning Task (NRDT) [4], taking into account the inconvenience of necessary measurements, not considered in the previous research [5]. The results are applicable for redimensioning of every (virtual) circuit switching telecommunication system, both for wireline and wireless systems (GSM, PSTN, ISDN and BISDN). For packet - switching networks proposed approach may be used as a comparison basis and when they work in circuit switching mode (e.g. VoIP).

Trained Neural Network Characterizing Variables for Predicting Organic Retention by Nanofiltration Membranes

Many organic compounds cause an irreversible damage to human health and the ecosystem and are present in water resources. Among these hazard substances, phenolic compounds play an important role on the actual contamination. Utilization of membrane technology is increasing exponentially in drinking water production and waste water treatment. The removal of organic compounds by nanofiltration membranes is characterized not only by molecular sieving effects but also by membrane-solute interactions. Influence of the sieving parameters (molecular weight and molecular diameter) and the physicochemical interactions (dissociation constant and molecular hydrophobicity) on the membrane rejection of the organic solutes were studied. The molecular hydrophobicity is expressed as logarithm of octanol-water partition coefficient. This paper proposes a method used that can be used for symbolic knowledge extraction from a trained neural network, once they have been trained with the desired performance and is based on detect the more important variables in problems where exist multicolineality among the input variables.

Classification of Data to Extract Knowledge from Neural Networks

A major drawback of artificial neural networks is their black-box character. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, we use a method that can be used for symbolic knowledge extraction from neural networks, once they have been trained with desired function. The basis of this method is the weights of the neural network trained. This method allows knowledge extraction from neural networks with continuous inputs and output as well as rule extraction. An example of the application is showed. This example is based on the extraction of average load demand of a power plant.

Progmosis:evaluating risky individual behavior during epidemics using mobile network data

The possibility to analyze, quantify and forecast epidemic outbreaks is fundamental when devising effective disease containment strategies. Policy makers are faced with the intricate task of drafting realistically implementable policies that strike a balance between risk management and cost. Two major techniques policy makers have at their disposal are: epidemic modeling and contact tracing. Models are used to forecast the evolution of the epidemic both globally and regionally, while contact tracing is used to reconstruct the chain of people who have been potentially infected, so that they can be tested, isolated and treated immediately. However, both techniques might provide limited information, especially during an already advanced crisis when the need for action is urgent. In this paper we propose an alternative approach that goes beyond epidemic modeling and contact tracing, and leverages behavioral data generated by mobile carrier networks to evaluate contagion risk on a per-user basis. The individual risk represents the loss incurred by not isolating or treating a specific person, both in terms of how likely it is for this person to spread the disease as well as how many secondary infections it will cause. To this aim, we develop a model, named Progmosis, which quantifies this risk based on movement and regional aggregated statistics about infection rates. We develop and release an open-source tool that calculates this risk based on cellular network events. We simulate a realistic epidemic scenarios, based on an Ebola virus outbreak; we find that gradually restricting the mobility of a subset of individuals reduces the number of infected people after 30 days by 24%.

Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM

One major drawback of coherent optical orthogonal frequency-division multiplexing (CO-OFDM) that hitherto remains unsolved is its vulnerability to nonlinear fiber effects due to its high peak-to-average power ratio. Several digital signal processing techniques have been investigated for the compensation of fiber nonlinearities, e.g., digital back-propagation, nonlinear pre- and post-compensation and nonlinear equalizers (NLEs) based on the inverse Volterra-series transfer function (IVSTF). Alternatively, nonlinearities can be mitigated using nonlinear decision classifiers such as artificial neural networks (ANNs) based on a multilayer perceptron. In this paper, ANN-NLE is presented for a 16QAM CO-OFDM system. The capability of the proposed approach to compensate the fiber nonlinearities is numerically demonstrated for up to 100-Gb/s and over 1000km and compared to the benchmark IVSTF-NLE. Results show that in terms of Q-factor, for 100-Gb/s at 1000km of transmission, ANN-NLE outperforms linear equalization and IVSTF-NLE by 3.2dB and 1dB, respectively.

Application of support vector machines on the basis of the first Hungarian bankruptcy model

In our study we rely on a data mining procedure known as support vector machine (SVM) on the database of the first Hungarian bankruptcy model. The models constructed are then contrasted with the results of earlier bankruptcy models with the use of classification accuracy and the area under the ROC curve. In using the SVM technique, in addition to conventional kernel functions, we also examine the possibilities of applying the ANOVA kernel function and take a detailed look at data preparation tasks recommended in using the SVM method (handling of outliers). The results of the models assembled suggest that a significant improvement of classification accuracy can be achieved on the database of the first Hungarian bankruptcy model when using the SVM method as opposed to neural networks.

The network structure of Hungarian business clusters

This article investigates the attitudes to inter-firm co-operation in Hungary by analysing a special group of business networks: the business clusters. Following an overview of cluster policy, a wide range of selfproclaimed business clusters are identified. A small elite of these business networks evolves into successful, sustainable innovative business clusters. However, in the majority of cases, these consortia of interfirm co-operation are not based on a mutually satisfactory model, and as a consequence, many clusters do not survive in the longer term. The paper uses the concepts and models of social network theory in order to explain, why and under what circumstances inter-firm co-operation in clusters enhances the competitiveness of the network as a whole, or alternatively, under what circumstances the cluster remains dependent on Government subsidies. The empirical basis of the study is a thorough internet research about the Hungarian cluster movement; a questionnaire based expert survey among managers of clusters and member companies and a set of in-depth interviews among managers of self-proclaimed clusters. The last chapter analyises the applicability of social network theory in the analysis of business networks and a model involving the value chain is recommended.

Metropolitan Tourism Experience Development. Selected studies from the Tourism Network Workshop of the Regional Studies Association, held in Budapest, Hungary, 2015

On January 28-30, 2015 Corvinus University of Budapest hosted the latest workshop of the Regional Studies Association’s Tourism Research Network. The event had been held previously in Izmir, Aalborg, Warsaw, Östersund, Antalya, Leeds and Vila-seca Catalonia. The aim of the RSA research network is to examine tourism diversity from the perspective of regional development in order to identify current challenges and opportunities in a systematic manner, and hence provide the basis for a more well-informed integration of tourism in regional development strategies and move beyond political short-termism and buzzword fascination. In the frame of the network a series of workshops have been organised from various topics of destination management till rural tourism.

A novel neural network based system for assessing risks associated with information technology security breaches

Security remains a top priority for organizations as their information systems continue to be plagued by security breaches. This dissertation developed a unique approach to assess the security risks associated with information systems based on dynamic neural network architecture. The risks that are considered encompass the production computing environment and the client machine environment. The risks are established as metrics that define how susceptible each of the computing environments is to security breaches. ^ The merit of the approach developed in this dissertation is based on the design and implementation of Artificial Neural Networks to assess the risks in the computing and client machine environments. The datasets that were utilized in the implementation and validation of the model were obtained from business organizations using a web survey tool hosted by Microsoft. This site was designed as a host site for anonymous surveys that were devised specifically as part of this dissertation. Microsoft customers can login to the website and submit their responses to the questionnaire. ^ This work asserted that security in information systems is not dependent exclusively on technology but rather on the triumvirate people, process and technology. The questionnaire and consequently the developed neural network architecture accounted for all three key factors that impact information systems security. ^ As part of the study, a methodology on how to develop, train and validate such a predictive model was devised and successfully deployed. This methodology prescribed how to determine the optimal topology, activation function, and associated parameters for this security based scenario. The assessment of the effects of security breaches to the information systems has traditionally been post-mortem whereas this dissertation provided a predictive solution where organizations can determine how susceptible their environments are to security breaches in a proactive way. ^

A static traffic assignment model combined with an artificial neural network delay model

As traffic congestion continues to worsen in large urban areas, solutions are urgently sought. However, transportation planning models, which estimate traffic volumes on transportation network links, are often unable to realistically consider travel time delays at intersections. Introducing signal controls in models often result in significant and unstable changes in network attributes, which, in turn, leads to instability of models. Ignoring the effect of delays at intersections makes the model output inaccurate and unable to predict travel time. To represent traffic conditions in a network more accurately, planning models should be capable of arriving at a network solution based on travel costs that are consistent with the intersection delays due to signal controls. This research attempts to achieve this goal by optimizing signal controls and estimating intersection delays accordingly, which are then used in traffic assignment. Simultaneous optimization of traffic routing and signal controls has not been accomplished in real-world applications of traffic assignment. To this end, a delay model dealing with five major types of intersections has been developed using artificial neural networks (ANNs). An ANN architecture consists of interconnecting artificial neurons. The architecture may either be used to gain an understanding of biological neural networks, or for solving artificial intelligence problems without necessarily creating a model of a real biological system. The ANN delay model has been trained using extensive simulations based on TRANSYT-7F signal optimizations. The delay estimates by the ANN delay model have percentage root-mean-squared errors (%RMSE) that are less than 25.6%, which is satisfactory for planning purposes. Larger prediction errors are typically associated with severely oversaturated conditions. A combined system has also been developed that includes the artificial neural network (ANN) delay estimating model and a user-equilibrium (UE) traffic assignment model. The combined system employs the Frank-Wolfe method to achieve a convergent solution. Because the ANN delay model provides no derivatives of the delay function, a Mesh Adaptive Direct Search (MADS) method is applied to assist in and expedite the iterative process of the Frank-Wolfe method. The performance of the combined system confirms that the convergence of the solution is achieved, although the global optimum may not be guaranteed.

Social network structure as a critical success condition for open source software project communities

In recent years, a surprising new phenomenon has emerged in which globally-distributed online communities collaborate to create useful and sophisticated computer software. These open source software groups are comprised of generally unaffiliated individuals and organizations who work in a seemingly chaotic fashion and who participate on a voluntary basis without direct financial incentive. ^ The purpose of this research is to investigate the relationship between the social network structure of these intriguing groups and their level of output and activity, where social network structure is defined as (1) closure or connectedness within the group, (2) bridging ties which extend outside of the group, and (3) leader centrality within the group. Based on well-tested theories of social capital and centrality in teams, propositions were formulated which suggest that social network structures associated with successful open source software project communities will exhibit high levels of bridging and moderate levels of closure and leader centrality. ^ The research setting was the SourceForge hosting organization and a study population of 143 project communities was identified. Independent variables included measures of closure and leader centrality defined over conversational ties, along with measures of bridging defined over membership ties. Dependent variables included source code commits and software releases for community output, and software downloads and project site page views for community activity. A cross-sectional study design was used and archival data were extracted and aggregated for the two-year period following the first release of project software. The resulting compiled variables were analyzed using multiple linear and quadratic regressions, controlling for group size and conversational volume. ^ Contrary to theory-based expectations, the surprising results showed that successful project groups exhibited low levels of closure and that the levels of bridging and leader centrality were not important factors of success. These findings suggest that the creation and use of open source software may represent a fundamentally new socio-technical development process which disrupts the team paradigm and which triggers the need for building new theories of collaborative development. These new theories could point towards the broader application of open source methods for the creation of knowledge-based products other than software. ^

Neural network based off-line handwritten text recognition system

This dissertation introduces a new system for handwritten text recognition based on an improved neural network design. Most of the existing neural networks treat mean square error function as the standard error function. The system as proposed in this dissertation utilizes the mean quartic error function, where the third and fourth derivatives are non-zero. Consequently, many improvements on the training methods were achieved. The training results are carefully assessed before and after the update. To evaluate the performance of a training system, there are three essential factors to be considered, and they are from high to low importance priority: (1) error rate on testing set, (2) processing time needed to recognize a segmented character and (3) the total training time and subsequently the total testing time. It is observed that bounded training methods accelerate the training process, while semi-third order training methods, next-minimal training methods, and preprocessing operations reduce the error rate on the testing set. Empirical observations suggest that two combinations of training methods are needed for different case character recognition. Since character segmentation is required for word and sentence recognition, this dissertation provides also an effective rule-based segmentation method, which is different from the conventional adaptive segmentation methods. Dictionary-based correction is utilized to correct mistakes resulting from the recognition and segmentation phases. The integration of the segmentation methods with the handwritten character recognition algorithm yielded an accuracy of 92% for lower case characters and 97% for upper case characters. In the testing phase, the database consists of 20,000 handwritten characters, with 10,000 for each case. The testing phase on the recognition 10,000 handwritten characters required 8.5 seconds in processing time.