Neural networks for routing of communication networks withunreliable components

A new neural network model, Routron, which can handle dependent component failures of communication networks, is proposed. We prove that the proposed Routron has a stable solution. Moreover, useful upper and lower bounds for the design parameters are derived to help select them in implementations. Simulation results are included to illustrate the effectiveness of the algorithm.     

EOR project networks

This paper considers project networks all of whose nodes have an exclusive-or entrance and whose arc weights consist of the execution probabilities and distribution functions of the durations of the respective project activities. EOR networks have some nice properties, for example, a set of Markov renewal processes can be assigned to such a network. The renewal functions of those processes correspond to special activation functions of the network and can (approximately) be computed very efficiently. At last a method for the complete evaluation of an EOR project network in the sense of time planning is presented.     

Neural networks for finite constraint satisfaction

Constraint Satisfaction Problems (CSPs) are in general NP-hard, and a general deterministic polynomial time algorithm is not known. They play a central role in real-life problems. The satisfaction of a Conjunctive Normal Form (CNF-SAT)is the core of any CSP. We present a new modelisation technique for any CSP with finite variable domains, and, in particular, for solving CNF-SAT. The knowledge representation is based on two fundamental types of constraint: the choice constraint, and the exclusion constraint. These models are then implemented by means of several different neural networks, some based on backpropagation learning and others on different procedures. All these networks are trained through a supervised procedure, and learn to efficiently solve CNF-SAT. The results of significant tests are described: they show that some networks can effectively solve the proposed problems.     

Neural networks for convex hull computation

Computing convex hull is one of the central problems in various applications of computational geometry. In this paper, a convex hull computing neural network (CHCNN) is developed to solve the related problems in the N-dimensional spaces. The algorithm is based on a two-layered neural network, topologically similar to ART, with a newly developed adaptive training strategy called excited learning. The CHCNN provides a parallel online and real-time processing of data which, after training, yields two closely related approximations, one from within and one from outside, of the desired convex hull. It is shown that accuracy of the approximate convex hulls obtained is around O[K^-1(N-1/)], where K is the number of neurons in the output layer of the CHCNN. When K is taken to be sufficiently large, the CHCNN can generate any accurate approximate convex hull. We also show that an upper bound exists such that the CHCNN will yield the precise convex hull when K is larger than or equal to this bound. A series of simulations and applications is provided to demonstrate the feasibility, effectiveness, and high efficiency of the proposed algorithm     

Neural networks for web content filtering

With the proliferation of harmful Internet content such as pornography, violence, and hate messages, effective content-filtering systems are essential. Many Web-filtering systems are commercially available, and potential users can download trial versions from the Internet. However, the techniques these systems use are insufficiently accurate and do not adapt well to the ever-changing Web. To solve this problem, we propose using artificial neural networks to classify Web pages during content filtering. We focus on blocking pornography because it is among the most prolific and harmful Web content. However, our general framework is adaptable for filtering other objectionable Web material.     

Neural networks for nonlinear state estimation

Estimating the state of a nonlinear stochastic system (observed through a nonlinear noisy measurement channel) has been the goal of considerable research to solve both filtering and control problems. In this paper, an original approach to the solution of the optimal state estimation problem by means of neural networks is proposed, which consists in constraining the state estimator to take on the structure of a multilayer feedforward network. Both non-recursive and recursive estimation schemes are considered, which enable one to reduce the original functional problem to a nonlinear programming one. As this reduction entails approximations for the optimal estimation strategy, quantitative results on the accuracy of such approximations are reported. Simulation results confirm the effectiveness of the proposed method.     

Neural networks for shortest path computation and routing incomputer networks

The application of neural networks to the optimum routing problem in packet-switched computer networks, where the goal is to minimize the network-wide average time delay, is addressed. Under appropriate assumptions, the optimum routing algorithm relies heavily on shortest path computations that have to be carried out in real time. For this purpose an efficient neural network shortest path algorithm that is an improved version of previously suggested Hopfield models is proposed. The general principles involved in the design of the proposed neural network are discussed in detail. Its computational power is demonstrated through computer simulations. One of the main features of the proposed model is that it will enable the routing algorithm to be implemented in real time and also to be adaptive to changes in link costs and network topology.     

A three-stage construction for multiconnection networks

Summary A multiconnection network of size N is a switching network with N inputs and N outputs which realizes multiconnections, i.e., connections between the N inputs and N outputs in such a way that every output is connected to exactly one input, but an input can be connected to an arbitrary number of outputs. That network is complete if it can realize all N ^N multiconnections. This structure generalizes the permutation network. We consider here the design of multiconnection networks by a three-stage Clos network using complete substitution networks as its building cells and we show that the resulting multiconnection network is complete if and only if the cells in the middle stage have size 2. Moreover, we describe the control algorithm for such a network. This leads to the design of cellular multiconnection networks of arbitrary size with a relatively simple control algorithm.     

Comparator networks for binary heap construction

Comparator networks for constructing binary heaps of size n are presented which have size and depth . A lower bound of for the size of any heap construction network is also proven, implying that the networks presented are within a constant factor of optimal. We give a tight relation between the leading constants in the size of selection networks and in the size of heap construction networks.     

Early communication key to software project success

The paper considers how customer/seller faulty communication causes many software development problems. At least part of this communications breakdown stems from customers' lack of comprehension regarding their role in the development process. Developers must help customers realize that software development is an inherently complex and uncertain activity that can only succeed through close cooperation     

Neural networks for engineering in medicine and biology

The September 1990 special use on neural networks of the IEEE Engineering in Medici and Biology Magazine is described. This issue contains of papers dealing with various aspects and applications of neural networks in a wide spectrum of biomedical engineering problems.     

Neural networks for the EMOBOT robot control architecture

Within the EMOBOT approach to adaptive behaviour, the task of learning to control the behaviour is one of the most interesting challenges. Learned action selection between classically implemented control mechanisms, with respect to internal values and sensor readings, provides a way to modulate a variety of behavioural capabilities. To demonstrate the potential of the learning emotional controller, we chose a 10-5-12 MLP to implement the , controller of the EMOBOT. Since no teacher vector is available for the chosen task, the neural network is trained with a reinforcement strategy. The emotion-value-dependent reinforcement signal, together with the output of the network, is the basis with which to compute an artificial teacher vector. Then, the established gradient descent method (backpropagation of error) is applied to train the neural network. First results obtained by extensive simulations show that a still unrevealed richness in behaviour can be realised when using the neural-network-based learning emotional controller.