A general framework for concurrent simulation on neural networkmodels

The analysis of complex neural network models via analytical techniques is often quite difficult due to the large numbers of components involved and the nonlinearities associated with these components. The authors present a framework for simulating neural networks as discrete event nonlinear dynamical systems. This includes neural network models whose components are described by continuous-time differential equations or by discrete-time difference equations. Specifically, the authors consider the design and construction of a concurrent object-oriented discrete event simulation environment for neural networks. The use of an object-oriented language provides the data abstraction facilities necessary to support modification and extension of the simulation system at a high level of abstraction. Furthermore, the ability to specify concurrent processing supports execution on parallel architectures. The use of this system is demonstrated by simulating a specific neural network model on a general-purpose parallel computer     

A general framework for time granularity and its application to temporal reasoning

This paper presents a general framework to define time granularity systems. We identify the main dimensions along which different systems can be characterized, and investigate the formal relationships among granularities in these systems. The paper also introduces the notion of a network of temporal constraints with (multiple) granularities emphasizing the semantic and computational differences from constraint networks with a single granularity. Consistency of networks with multiple granularities is shown to beNP‐hard in general and approximate solutions for this problem and for the minimal network problem are proposed. This revised version was published online in June 2006 with corrections to the Cover Date.     

A maximum likelihood framework for determining moving edges

The determination of moving edges in an image sequence is discussed. An approach is proposed that relies on modeling principles and likely hypothesis testing techniques. A spatiotemporal edge in an image sequence is modeled as a surface patch in a 3-D spatiotemporal space. A likelihood ratio test enables its detection as well as simultaneous estimation of its related attributes. It is shown that the computation of this test leads to convolving the image sequence with a set of predetermined masks. The emphasis is on a restricted but widely relevant and useful case of surface patch, namely the planar one. In addition, an implementation of the procedure whose computation cost is merely equivalent to a spatial gradient operator is presented. This method can be of interest for motion-analysis schemes, not only for supplying spatiotemporal segmentation, but also for extracting local motion information. Moreover, it can cope with occlusion contours and important displacement magnitude. Experiments have been carried out with both synthetic and real images     

A general framework for debugging

The state of the art of debugging is examined. A debugged process model that serves as the basis of a general debugging framework is described. The relationship of the model to traditional debugging processes and support tools is discussed. A minimal set of requirements for a general debugging framework is described in terms of both the theory behind debugging methodologies and the support tools. An execution monitor, Eden, that serves as a debugging tool within this general framework is described     

A self-adaptive computing framework for parallel maximum likelihood evaluation

Many scientific disciplines use maximum likelihood evaluation (MLE) as an analytical tool. As the data to be analyzed grows increasingly, MLE demands more parallelism to improve analysis efficiency. Unfortunately, it is difficult for scientists and engineers to develop their own distributed/parallelized MLE applications. In addition, self-adaptability is an important characteristic for computing-intensive application for improving efficiency. This paper presents a self-adaptive and parallelized MLE framework that consists of a master process and a set of worker processes on a distributed environment. The workers are responsible to compute tasks, while the master needs to merge the computing results, to initiate or to terminate another computing iteration, and to decide how to re-distribute the computing tasks to workers. The proposed approach uses neither any monitoring mechanism to collect system state nor load-balancing-decision mechanism to balancing the workload. Instead, it measures the performance of each worker for computing an iteration, and uses the information to adjust the workload of workers accordingly. The experimental results show that not only the proposed framework can adapt to environmental changes, but also the proposed framework is effective; even in a stable environment that is dedicated for one application, the proposed framework still demonstrates its significant improvement in self-adaptability. The self-adaptability will be significantly improved while the workload of computing machines unbalanced.     

A framework for neural net specification

A notation for the specification of neural nets is proposed. The aim is to produce a simple mathematical framework for use in specifying neural nets essentially by defining their transfer functions and connections. Nets are specified as interacting processing elements (nodes), communicating via instant links. Dynamics and adaptation are defined at the processing elements themselves, and all interaction is explicitly specified by directed arcs. Specifications can be built up hierarchically by turning a specification into a generator for a node, or they can be developed top-down. The use of the system is illustrated     

A general framework for architecture composability

Architectures depict design principles: paradigms that can be understood by all, allow thinking on a higher plane and avoiding low-level mistakes. They provide means for ensuring correctness by construction by enforcing global properties characterizing the coordination between components. An architecture can be considered as an operator A that, applied to a set of components \({\mathcal{B}}\), builds a composite component \({A(\mathcal{B})}\) meeting a characteristic property \({\Phi}\). Architecture composability is a basic and common problem faced by system designers. In this paper, we propose a formal and general framework for architecture composability based on an associative, commutative and idempotent architecture composition operator \({\oplus}\). The main result is that if two architectures A ₁ and A ₂ enforce respectively safety properties \({\Phi_{1}}\) and \({\Phi_{2}}\), the architecture \({A_{1} \oplus A_{2}}\) enforces the property \({\Phi_{1} \land \Phi_{2}}\), that is both properties are preserved by architecture composition. We also establish preservation of liveness properties by architecture composition. The presented results are illustrated by a running example and a case study.     

A general framework for reason maintenance

There are several different kinds of reason-maintenance system in existence, which provide rather different functionalities. I present a general structure that subsumes most such systems, and that allows some new behaviors to emerge. The general framework is based on logic-style clauses (disjunctions of literals) instead of justifications. Literals are tagged with labels that say what assumption sets make them true and false. Nonmonotonicity is implemented by allowing clauses to contain disjuncts of the form Lp, which supports propagation through a clause whenever p is not known to be true. The resulting system supports two popular styles of dependency-directed backtracking, using nogoods and assumption retraction. Assumption retraction does not require a separate contradiction-elimination phase, but occurs automatically during label propagation. Label propagation can be achieved by the usual variants of Boolean constraint propagation, provided there are no “odd loops” through the clauses, and it can be shown that the system itself never creates odd loops.     

An effective framework for characterizing rare categories

Rare categories become more and more abundant and their characterization has received little attention thus far. Fraudulent banking transactions, network intrusions, and rare diseases are examples of rare classes whose detection and characterization are of high value. However, accurate characterization is challenging due to high-skewness and nonseparability from majority classes, e.g., fraudulent transactions masquerade as legitimate ones. This paper proposes the RACH algorithm by exploring the compactness property of the rare categories. This algorithm is semi-supervised in nature since it uses both labeled and unlabeled data. It is based on an optimization framework which encloses the rare examples by a minimum-radius hyperball. The framework is then converted into a convex optimization problem, which is in turn effectively solved in its dual form by the projected subgradient method. RACH can be naturally kernelized. Experimental results validate the effectiveness of RACH.     

A neural framework for adaptive robot control

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.     

A general framework for relation graph clustering

Relation graphs, in which multi-type (or single type) nodes are related to each other, frequently arise in many important applications, such as Web mining, information retrieval, bioinformatics, and epidemiology. In this study, We propose a general framework for clustering on relation graphs. Under this framework, we derive a family of clustering algorithms including both hard and soft versions, which are capable of learning cluster patterns from relation graphs with various structures and statistical properties. A number of classic approaches on special cases of relation graphs, such as traditional graphs with singly-type nodes and bi-type relation graphs with two types of nodes, can be viewed as special cases of the proposed framework. The theoretic analysis and experiments demonstrate the great potential and effectiveness of the proposed framework and algorithm.     

A general framework for reasoning about change

The capability to represent and use concepts like time and events in computer science is essential to solve a wide class of problems characterized by the notion of change. Real-time, databases and multimedia are just a few of several areas which needs good tools to deal with time. Another area where this concepts are essential is artificial intelligence because an agent must be able to reason about a dynamic environment. In this work a formalism is proposed which allows the representation and use of several features that had been recognized as useful in the attempts to solve such class of problems. A general framework based on a many-sorted logic is proposed centering our attention in issues such as the representation of time, actions, properties, events and causality. The proposal is compared with related work from the temporal logic and artificial intelligence areas. This work complements and enhances previously related efforts on formalizing temporal concepts with the same purpose. Juan Carlos Augusto, Ph.D.: He is a Lecturer in the Department of Computer Science at Universidad Nacional del Sur (Argentina), where he graduated as Licenciado en Ciencias de la Computacion and Doctor en Ciencias de la Computacion. Currently on leave in the Department of Electronics and Computer Science, University of Southampton (United Kingdom). His research interests are focused in the dynamic aspects of computing systems. This involves solving conceptual problems related to the specification of time and change and designing tools to improve systems in several areas of computer science, such as artificial intelligence, databases, multimedia, software verification and real-time systems. He has been conducting research on temporal representation and reasoning since 1993. Throughout these years he had the opportunity to contribute to several research projects as a researcher and has head or co-head of research groups. Other activities and contributions to highlight are the organization of international events, editorial work and supervision of postgraduate students, all of which contributes to the generation and dissemination of knowledge about the dynamic aspects of computing systems.     

A general framework for computing block accesses

A physcial database system design should take account of skewed block access distributions, nonuniformly distributed attribute domains, and dependent attributes. In this paper we drive general formulas for the number of blocks accessed under these assumptions by considering a class of related occupancy problems. We then proceed to develop robust and accurate approximations for these formulas. We investigate three classes of approximation methods, respectively based on generating functions, Taylor series expansions, and majorization. These approximations are simple to use and more accurate than the cost estimate formulas generated by making uniformity and independence assumptions. Thus they are more representative of the actual database environment, and can be utilized by a query optimizer for better performance.     

A general framework for tackling the output regulation problem

Output regulation aims to achieve, in addition to closed-loop stability, asymptotic tracking and disturbance rejection for a class of reference inputs and disturbances. Thus, it poses a more challenging problem than stabilization. For over a decade, the nonlinear output regulation problem has been one of the focuses in nonlinear control research, and active research on this problem has generated many fruitful results. Nevertheless, there are two hurdles that impede the further progress of the research on the output regulation problem. The first one is the assumption that the solution or the partial solution of the regulator equations is polynomial. The second one is the lack of a systematic mechanism to handle the global robust output regulation problem. We establish a general framework that systematically converts the robust output regulation problem for a general nonlinear system into a robust stabilization problem for an appropriately augmented system. This general framework, on one hand, relaxes the polynomial assumption, and on the other hand, offers a greater flexibility to incorporate recent new stabilization techniques, thus setting a stage for systematically tackling the robust output regulation with global stability.     

A general framework for the evaluation of symbol recognition methods

Performance evaluation is receiving increasing interest in graphics recognition. In this paper, we discuss some questions regarding the definition of a general framework for evaluation of symbol recognition methods. The discussion is centered on three key elements in performance evaluation: test data, evaluation metrics and protocols of evaluation. As a result of this discussion we state some general principles to be taken into account for the definition of such a framework. Finally, we describe the application of this framework to the organization of the first contest on symbol recognition in GREC’03, along with the results obtained by the participants.     

A theoretical framework for multiple neural network systems

Multiple neural network systems have become popular techniques for tackling complex tasks, often giving improved performance compared to single network systems. For example, modular systems can provide improvements in generalisation through task decomposition, whereas multiple classifier and regressor systems typically improve generalisation through the ensemble combination of redundant networks. Whilst there has been significant focus on understanding the theoretical properties of some of these multi-net systems, particularly ensemble systems, there has been little theoretical work on understanding the properties of the generic combination of networks, important in developing more complex systems, perhaps even those a step closer to their biological counterparts. In this article, we provide a formal framework in which the generic combination of neural networks can be described, and in which the properties of the system can be rigorously analysed. We achieve this by describing multi-net systems in terms of partially ordered sets and state transition systems. By way of example, we explore an abstract version of learning applied to a generic multi-net system that can combine an arbitrary number of networks in sequence and in parallel. By using the framework we show with a constructive proof that, under specific conditions, if it is possible to train the generic system, then training can be achieved by the abstract technique described.     

A neural fuzzy framework for system mapping applications

A novel neural fuzzy (NF) mapping framework is developed in this paper to convert linear systems and a class of nonlinear systems from the crisp-domain to a NF representation. The resulting neural fuzzy system (NFS) is guaranteed to be functionally identical to the original system. Therefore, the proposed mapping technique provides a well-defined prototype for one type of NFS design. The resulting fuzzy reasoning representation facilitates the investigation in linguistic terms into the system operations, whereas the system performance can be further improved by properly incorporating expertise knowledge or by online/offline training via this NF structure. The developed technique is to extend our previously-developed techniques to NF modeling/mapping applications and its effectiveness is demonstrated by simulations using a flexible-link robot.