We present an evolvable model of modular neural networks which are rich in autonomy and creativity. In order to build an artificial neural network which is rich in autonomy and creativity, we have adopted the ideas an...
详细信息
We present an evolvable model of modular neural networks which are rich in autonomy and creativity. In order to build an artificial neural network which is rich in autonomy and creativity, we have adopted the ideas and methodologies of artificial life. The paper describes the concepts and methodologies for the evolvable model of modular neural networks, which will be able not only to develop new functionality spontaneously but also to grow and evolve its own structure autonomously. Although the ultimate goal of this model is to design the control system for such behavior based robots as Khepera, we have attempted to apply the mechanism to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong possibility to generate useful networkarchitectures from an initial set of randomly connected networks.
The use of a self-contained dual neural network architecture for the solution of nonlinear optimal control problems is investigated in this study. The network structure solves the dynamic programming equations in stag...
详细信息
The use of a self-contained dual neural network architecture for the solution of nonlinear optimal control problems is investigated in this study. The network structure solves the dynamic programming equations in stages and at the convergence, one network provides the optimal control and the second network provides a fault tolerance to the control system. We detail the steps in design and solve a linearized and a nonlinear, unstable, four-dimensional inverted pendulum on a cart problem. Numerical results are presented and compared with linearized optimal control. Unlike the previously published neural network solutions, this methodology does not need any external training, solves the nonlinear problem directly and provides a feedback control.
In this paper we report on a parallel/distributed virtual machine prototype called World-Wide Virtual Machine (WWVM) that is designed to attack grand challenge problems beyond the capabilities of a single supercompute...
详细信息
In this paper we report on a parallel/distributed virtual machine prototype called World-Wide Virtual Machine (WWVM) that is designed to attack grand challenge problems beyond the capabilities of a single supercomputer. The prototype is based on emerging Web and existing HPCC technologies and utilizes the pool of Web servers on the internet as a flexible, convenient, and inexpensive metacomputing resource. World-Wide web supplies a standard open interface to the world regardless of the machine type. Through this interface Web servers can be used either as computation nodes or coordinators managing other connected nodes of the virtual machine. We have constructed a Web-based parallel/distributed programming environment for solving metaproblems consisting of MPI and PVM message-passing programs and High Performance Fortran programs.
The article addresses the emerging technologies for developing network software. As networking technology has made great progress in its speed and connectivity in the past twenty years (1976-96), network software has ...
详细信息
The article addresses the emerging technologies for developing network software. As networking technology has made great progress in its speed and connectivity in the past twenty years (1976-96), network software has also evolved and many technologies have been tried and applied to network software development. Formal methods provide model verification, and some sorts of automatic program generation and artificial intelligence open the new arena of intelligent network software. Object oriented technology is coming into practice and enhances the maintainability and reuse of software. Recently, emerging technologies such as distributed objects, mobile agents, Java and networkprogramming will redefine the concept of network software and its development methodology. Commemorating the twentieth COMPSAC, the article summarizes these twenty years' experience and discusses future directions of network software development.
This paper describes the design and implementation of a conversion tool. This tool, called Distributed Computing Environment (DCE) Porting Tool, converts an opennetwork Computing (ONC) Remote Procedure Call (RPC) app...
详细信息
This paper describes the design and implementation of a conversion tool. This tool, called Distributed Computing Environment (DCE) Porting Tool, converts an opennetwork Computing (ONC) Remote Procedure Call (RPC) application to a DCE RPC application. The manual intervention needed during the conversion process in minimal. The paper briefly describes RPC programming and highlights the difference between ONC RPC and DCE RPC. The design decisions of the Porting Tool is explained. The implementation uses LEX and YACC (language processing tools supported by Unix) for conversion logic and OSF/MOTIF for Graphical User Interface (GUI). The paper concludes with current limitations of the Tool and the possible future work.
In today's high performance computing arena, there is a strong trend toward building virtual computers from heterogeneous resources on a network. In this paper we describe our experiences in building a world-wide ...
详细信息
ISBN:
(纸本)9780897918541
In today's high performance computing arena, there is a strong trend toward building virtual computers from heterogeneous resources on a network. In this paper we describe our experiences in building a world-wide virtual machine (WWVM) based on emerging Web and existing HPCC technologies. We have constructed a Web-based parallel/distributed programming environment on top of this machine demonstrating MPI and PVM message-passing programs and High Performance Fortran programs. Alternatively, the WWVM can be configured as a metacomputer for the solution of metaproblems.
Today many countries are aiming for the establishment of national information infrastructures in order to satisfy the emerging needs of the upcoming information society. This infrastructure should provide the foundati...
详细信息
Today many countries are aiming for the establishment of national information infrastructures in order to satisfy the emerging needs of the upcoming information society. This infrastructure should provide the foundation of an "electronic marketplace", where information services and telecommunication services will be offered by competitive service providers to arbitrary customers. The rapid and customized provision of services, which we call "intelligence on demand" represents an important prerequisite for the realization of a dynamic market place. In this context the concept of "mobile service agents" offers a new paradigm for the rapid and customized provision of services in open distributed processing environments. We illustrate the differences between telecommunication services based on the traditional, i.e. RPC-based client/server paradigm, and service implementations based on mobile service agents. We also discuss architectural principles and requirements of a distributed agent environment supporting mobile service agents. To show the benefits of mobile agent technology and specifically its application for the realization of mobile service agents, the paper addresses the impact of the mobile service agent concept on existing and upcoming telecommunication architectures such as IN, TMN and TINA.
The paper describes engineering a system for a distributed Austrian Alpine road-pricing environment as well as the structure and organization of the software development. The client/server-based road-pricing system, h...
详细信息
The paper describes engineering a system for a distributed Austrian Alpine road-pricing environment as well as the structure and organization of the software development. The client/server-based road-pricing system, handling on average 1.2 million vehicle transitions per month, had be to operational within a mere eight months after the start of the project. Current practical and industrial problems of client/server system strategies are discussed. Our main theses derived from the presented case study are: in current medium to large software engineering tasks there is a need for a) technical specialists for industrially identified project stress points (database, network, front-end) with experience in large projects, b) a project and process plan for a (very) short development time frame before production, and c) a dynamic production-oriented process model rather than a traditional linear process model.
The application of artificial neural networks (ANN) in real-time embedded systems demands high performance computers. Miniaturized massively parallel architectures are suitable computation platforms for this task. An ...
详细信息
ISBN:
(纸本)0780320182
The application of artificial neural networks (ANN) in real-time embedded systems demands high performance computers. Miniaturized massively parallel architectures are suitable computation platforms for this task. An important question which arises is how to establish an effective mapping from ANN algorithms to hardware. In this paper, we demonstrate how an effective mapping can be achieved with our programming environment in close combination with an optimized architecture design targeted for neuro-computing.
This paper proposes an object oriented method applied to the design of network protocols, telecommunication services and network management information architectures. This method is based on the concept of object orie...
详细信息
This paper proposes an object oriented method applied to the design of network protocols, telecommunication services and network management information architectures. This method is based on the concept of object oriented generic models. A generic model is a common structure applicable to the design of all the components of a given application. Generic models are proposed for each of the considered application domains.
暂无评论