Neural networks and seasonality: Some technical considerations

Debate continues regarding the capacity of feedforward neural networks (NNs) to deal with seasonality without pre-processing. The purpose of this paper is to provide, with examples, some theoretical perspective for the debate. In the first instance it considers possible specification errors arising through use of autoregressive forms. Secondly, it examines seasonal variation in the context of the so-called ‘universal approximation’ capabilities of NNs, finding that a short (bounded) sinusoidal series is easy for the network but that a series with many turning points becomes progressively more difficult. This follows from results contained in one of the seminal papers on NN approximation. It is confirmed in examples which also show that, to model seasonality with NNs, very large numbers of hidden nodes may be required.     

Neural networks and finite-order approximations

Email: Curry{at}Cardiff.ac.uk This paper investigates the approximation properties of standardfeedforward neural networks (NNs) through the application ofmultivanate Thylor-series expansions. The capacity to approximatearbitrary functional forms is central to the NN philosophy,but is usually proved by allowing the number of hidden nodesto increase to infinity. The Thylor-series approach does notdepend on such limiting cases, lie paper shows how the seriesapproximation depends on individual network weights. The roleof the bias term is taken as an example. We are also able tocompare the sigmoid and hyperbolic-tangent activation functions,with particular emphasis on their impact on the bias term. Thepaper concludes by discussing the potential importance of ourresults for NN modelling: of particular importance is the trainingprocess.     

Neural networks for a class of bi-level variational inequalities

In this paper, a class of bi-level variational inequalities for describing some practical equilibrium problems, which especially arise from engineering, management and economics, is presented, and a neural network approach for solving the bi-level variational inequalities is proposed. The energy function and neural dynamics of the proposed neural network are defined in this paper, and then the existence of the solution and the asymptotic stability of the neural network are shown. The simulation algorithm is presented and the performance of the proposed neural network approach is demonstrated by some numerical examples.     

A quantum metric of organizational performance: Terrorism and counterterrorism

Political terrorism and insurgency have become the primary means of global war among states. Lacking comparable military and political means to compete directly with Western civilization, many failed states and tribes have honed the art of asymmetric warfare. But traditional models of organizations do not work under normal or these extreme circumstances, precluding realistic models of terrorism and a fruitful search among alternatives for potential solutions. In contrast to traditional models, we have made substantial progress with a quantum model of organizations, which we further develop in this study with the introduction of a case study of a normal organization in the process of being restructured. We apply preliminary results from our model to terrorist organizations and counter terrorism.     

Modeling centralized organization of organizational change

Organizations change with the dynamics of the world. To enable organizations to change, certain structures and capabilities are needed. As all processes, a change process has an organization of its own. In this paper it is shown how within a formal organization modeling approach also organizational change processes can be modeled. A generic organization model (covering both organization structure and behavior) for organizational change is presented and formally evaluated for a case study. This model takes into account different phases in a change process considered in Organization Theory literature, such as unfreezing, movement and refreezing. Moreover, at the level of individuals, the internal beliefs and their changes are incorporated in the model. In addition, an internal mental model for (reflective) reasoning about expected role behavior is included in the organization model.     

Neural networks approach for determining total claim amounts in insurance

In this study, we present an approach based on neural networks, as an alternative to the ordinary least squares method, to describe the relation between the dependent and independent variables. It has been suggested to construct a model to describe the relation between dependent and independent variables as an alternative to the ordinary least squares method. A new model, which contains the month and number of payments, is proposed based on real data to determine total claim amounts in insurance as an alternative to the model suggested by Rousseeuw et al. (1984) [Rousseeuw, P., Daniels, B., Leroy, A., 1984. Applying robust regression to insurance. Insurance: Math. Econom. 3, 67–72] in view of an insurer.     

B_a空间中神经网络和平移网络的逼近

讨论了具一个隐层单元的神经网络在B_a空间中逼近的特征性定理并给出了逼近估计.对于平移网络,建立了Favard型估计.Orlicz空间中的相应结果均作为应用而给出.     

The impact of special days in call arrivals forecasting: A neural network approach to modelling special days

A key challenge for call centres remains the forecasting of high frequency call arrivals collected in hourly or shorter time buckets. In addition to the complex intraday, intraweek and intrayear seasonal cycles, call arrival data typically contain a large number of anomalous days, driven by the occurrence of holidays, special events, promotional activities and system failures. This study evaluates the use of a variety of univariate time series forecasting methods for forecasting intraday call arrivals in the presence of such outliers. Apart from established, statistical methods, we consider artificial neural networks (ANNs). Based on the modelling flexibility of the latter, we introduce and evaluate different methods to encode the outlying periods. Using intraday arrival series from a call centre operated by one of Europe’s leading entertainment companies, we provide new insights on the impact of outliers on the performance of established forecasting methods. Results show that ANNs forecast call centre data accurately, and are capable of modelling complex outliers using relatively simple outlier modelling approaches. We argue that the relative complexity of ANNs over standard statistical models is offset by the simplicity of coding multiple and unknown effects during outlying periods.     

B_a空间中神经网络和平移网络的逼近

讨论了具一个隐层单元的神经网络在Ba空间中逼近的特征性定理并给出了逼近估计.对于平移网络,建立了Favard型估计.Orlicz空间中的相应结果均作为应用而给出.     

Measuring agility of networked organizational structures via network entropy and mutual information

While the agility of networked organizational structures is important for organizational performance, studies on how to evaluate it remain scant, probably because the difficulty in measuring network evolution. In this conceptual paper, we propose two measures - network entropy and mutual information - to characterize the agility of networked organizational structure. Rooted in graph theory and information theory, these two measures capture network evolution in a comprehensive and parsimonious way. They indicate the uncertainty (or disorder) at the network level as well as the degree distribution at the individual level. We also propose an algorithm for applying them in the scenario of adding links to a network while holding the number of nodes fixed. Both simulated and real networks are used for demonstration. Implications and areas for future research are discussed in the end.     

Modeling pathways of differentiation in genetic regulatory networks with Boolean networks

We have carried out the first examination of pathways of cell differentiation in model genetic networks in which cell types are assumed to be attractors of the nonlinear dynamics, and differentiation corresponds to a transition of the cell to a new basin of attraction, which may be induced by a signal or noise perturbation. The associated flow along a transient to a new attractor corresponds to a pathway of differentiation. We have measured a variety of features of such model pathways of differentiation, most of which should be observable using gene array techniques. © 2005 Wiley Periodicals, Inc. Complexity 11: 52–60, 2005     

基于神经网络的期货市场预测及模型实现

通过对期货市场的研究,尝试用人工神经网络预测期货行情走势.介绍了如何将期货市场与改进的BP网络有机结合起来构造适合期价预测的模型,并应用Matlab工具,设计一个具有较强通用性的人工神经网络模型,在降低重复开发的同时,为更多潜在的用户提供一个适合各自需求的人工神经网络.通过实例证实运用神经网络进行期货价格预测相对于传统的经济预测方法具有更好的精确性.     

Modeling the complexity of genetic networks: Understanding multigenic and pleiotropic regulation

Molecular genetics presents an increasingly complex picture of the genome and biological function. Evidence is mounting for distributed function, redundancy, and combinatorial coding in the regulation of genes. Satisfactory explanation will require the concept of a parallel processing signaling network. Here we provide an introduction to Boolean networks and their relevance to present-day experimental research. Boolean network models exhibit global complex behavior, self-organization, stability, redundancy and periodicity, properties that deeply characterize biological systems. While the life sciences must inevitably face the issue of complexity, we may well look to cybernetics for a modeling language such as Boolean networks which can manageably describe parallel processing biological systems and provide a framework for the growing accumulation of data. We finally discuss experimental strategies and database systems that will enable mapping of genetic networks. The synthesis of these approaches holds an immense potential for new discoveries on the intimate nature of genetic networks, bringing us closer to an understanding of complex molecular physiological processes like brain development, and intractable medical problems of immediate importance, such as neurodegenerative disorders, cancer, and a variety of genetic diseases.     

Shape up or ship out: social networks,turnover, and organizational culture

This paper considers a formal model of cultural transmission in organizations, examining the interplay of structured social influence and organizational demography. A set of focused and fine-grained computational experiments elucidates this model’s assumptions, facilitates deeper explanations for some of its behavior, and explores the robustness and scope conditions of previously published conclusions. In doing so, this investigation highlights several important issues in the design and evaluation of computational experiments.

Neural networks and reaction-diffusion systems with prescribed dynamics

Reaction-diffusion systems and neural networks are considered. We prove that they can produce any structurally stable inertial dynamics.     

An application of Liapunov''s method for the analysis of neural networks

The stability is studied of a class of nonlinear dynamical systems which possess many nonlinearities and many equilibrium states. As a special case, the analyzed class of systems includes analog neural networks. Sufficient conditions for the nonoscillatory behaviour of these systems, in the form of frequency domain criteria, are presented. The main result is proved relying on a suitable Liapunov function which is subsequently used for the simultaneous computation of regions of attraction for each stable equilibrium.     

Robust global synchronization of complex networks with neutral-type delayed nodes

In this paper, the problems of robust global exponential synchronization for a class of complex networks with time-varying delayed couplings are considered. Each node in the network is composed of a class of delayed neural networks described by a nonlinear delay differential equation of neutral-type. Since model errors commonly exist in practical applications, the parameter uncertainties are involved in the considered model. Sufficient conditions that ensure the complex networks to be robustly globally exponentially synchronized are obtained by using the Lyapunov functional method and some properties of Kronecker product. An illustrative example is presented to show the effectiveness of the proposed approach.     

时滞Hopfield神经网络的全局指数稳定性

利用时滞微分不等式，讨论了时滞Ｈｏｐｆｉｅｌｄ神经网络的全局指数稳定性，获得了几个判定条件。这些结论推广了已知文献中的结果。     

神经网络的加权本质逼近阶

证明了具有单一隐层的神经网络在L_ω~q的逼近,获得了网络逼近的上界估计和下界估计.这一结果揭示了神经网络在加权逼近的意义下,网络的收敛阶与隐层单元个数之间的关系,为神经网络的应用提供了重要的理论基础.     

Sensitivity of chemical reaction networks: A structural approach. 3. Regular multimolecular systems

We present a systematic mathematical analysis of the qualitative steady‐state response to rate perturbations in large classes of reaction networks. This includes multimolecular reactions and allows for catalysis, enzymatic reactions, multiple reaction products, nonmonotone rate functions, and non‐closed autonomous systems. Our structural sensitivity analysis is based on the stoichiometry of the reaction network, only. It does not require numerical data on reaction rates. Instead, we impose mild and generic nondegeneracy conditions of algebraic type. From the structural data, only, we derive which steady‐state concentrations are sensitive to, and hence influenced by, changes of any particular reaction rate—and which are not. We also establish transitivity properties for influences involving rate perturbations. This allows us to derive an influence graph which globally summarizes the influence pattern of any given network. The influence graph allows the computational, but meaningful, automatic identification of functional subunits in general networks, which hierarchically influence each other. We illustrate our results for several variants of the glycolytic citric acid cycle. Biological applications include enzyme knockout experiments and metabolic control.