Search

Abstract To enhance the individual control performance over the standalone control of each process in mass production, this paper explores information sharing among processes by proposing an incremental inter-agent learning (IIAL) method for the online estimation of the process model in the adaptive control of a class of processes modeled by linear-in-unknown-constant-parameters (LIP) formulae. Each individual process control system makes use of information from its own and other processes incrementally with time and across process. The application of the proposed work to a single layer RBF neural networks adaptive control shows that the speed of tracking error convergence of each process is improved. [ABSTRACT FROM AUTHOR]

Abstract: The discrete delayed Hopfield neural networks is an extension of the discrete Hopfield neural networks. In this paper, the convergence of discrete delayed Hopfield neural networks is mainly studied, and some results on the convergence are obtained by using Lyapunov function. Several new sufficient conditions for the delayed networks converging towards a limit cycle with period at most 2 are proved in parallel updating mode. Also, some conditions for the delayed networks converging towards a limit cycle with 2-period are investigated in parallel updating mode. All results established in this paper extend the previous results on the convergence of both the discrete Hopfield neural networks, and the discrete delayed Hopfield neural networks in parallel updating mode. [Copyright &y& Elsevier]

Backpropagation (BP) algorithm is the typical strategy to train the feedforward neural networks (FNNs). Gradient descent approach is the popular numerical optimal method which is employed to implement the BP algorithm. However, this technique frequently leads to poor generalization and slow convergence. Inspired by the sparse response character of human neuron system, several sparse-response BP algorithms were developed which effectively improve the generalization performance. The essential idea is to impose the responses of hidden layer as a specific L 1 penalty term on the standard error function of FNNs. In this paper, we mainly focus on the two remaining challenging tasks: one is to solve the non-differential problem of the L 1 penalty term by introducing smooth approximation functions. The other aspect is to provide a rigorous convergence analysis for this novel sparse response BP algorithm. In addition, an illustrative numerical simulation has been done to support the theoretical statement. [ABSTRACT FROM AUTHOR]

Weight elimination offers a simple and efficient improvement of training algorithm of feedforward neural networks. It is a general regularization technique in terms of the flexible scaling parameters. Actually, the weight elimination technique also contains the weight decay regularization for a large scaling parameter. Many applications of this technique and its improvements have been reported. However, there is little research concentrated on its convergence behavior. In this paper, we theoretically analyze the weight elimination for cyclic learning method and determine the conditions for the uniform boundedness of weight sequence, and weak and strong convergence. Based on the assumed network parameters, the optimal choice for the scaling parameter can also be determined. Moreover, two illustrative simulations have been done to support the theoretical explorations as well. [ABSTRACT FROM AUTHOR]

Abstract: This paper is concerned with boundedness, convergence of solution of a class of non-autonomous discrete-time delayed Hopfield neural network model. Using the inequality technique, we obtain some sufficient conditions ensuring the boundedness of solutions of the discrete-time delayed Hopfield models in time-varying situation. Then, by exploring intrinsic features between non-autonomous system and its asymptotic equations, several novel sufficient conditions are established to ensure that all solutions of the networks converge to the solution of its asymptotic equations. Especially, for case of asymptotic autonomous system or asymptotic periodic system, we obtain some sufficient conditions ensuring all solutions of original system convergent to equilibrium or periodic solution of asymptotic system, respectively. An example is provided for demonstrating the effectiveness of the global stability conditions presented. Our results are not only presented in terms of system parameters and can be easily verified but also are less restrictive than previously known criteria. [Copyright &y& Elsevier]

This paper is concerned with a delay differential system with piecewise constant nonlinearity. Such a differential system can be regarded as a model of two-neuron artificial neural network with delayed feedback. Some interesting results are obtained for the convergence and periodicity of solutions of the system. [Copyright &y& Elsevier]

The main propose of this paper is to develop two neural network models for solving nonsingular multi-linear tensor system. Theoretical analysis shows that each of the neural network models ensures the convergence performance. For possible hardware implementation of the proposed neural network models, based on digital circuits, we adopt the Euler-type difference rule to discretize the corresponding Gradient neural network (GNN) models. The computer simulation results further substantiate that the models can solve a multi-linear system with nonsingular tensors. [ABSTRACT FROM AUTHOR]