Action research at the Sea Fish Industry Authority:improving the quality of our knowing- how do practices achieve organisational learning and renewal and how does this change overtime?

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT

Curvature-driven smoothing: a learning algorithm for feed-forward networks

The performance of feed-forward neural networks in real applications can be often be improved significantly if use is made of a-priori information. For interpolation problems this prior knowledge frequently includes smoothness requirements on the network mapping, and can be imposed by the addition to the error function of suitable regularization terms. The new error function, however, now depends on the derivatives of the network mapping, and so the standard back-propagation algorithm cannot be applied. In this paper, we derive a computationally efficient learning algorithm, for a feed-forward network of arbitrary topology, which can be used to minimize the new error function. Networks having a single hidden layer, for which the learning algorithm simplifies, are treated as a special case.

A Bayesian perspective on stochastic neurocontrol

Control design for stochastic uncertain nonlinear systems is traditionally based on minimizing the expected value of a suitably chosen loss function. Moreover, most control methods usually assume the certainty equivalence principle to simplify the problem and make it computationally tractable. We offer an improved probabilistic framework which is not constrained by these previous assumptions, and provides a more natural framework for incorporating and dealing with uncertainty. The focus of this paper is on developing this framework to obtain an optimal control law strategy using a fully probabilistic approach for information extraction from process data, which does not require detailed knowledge of system dynamics. Moreover, the proposed control method framework allows handling the problem of input-dependent noise. A basic paradigm is proposed and the resulting algorithm is discussed. The proposed probabilistic control method is for the general nonlinear class of discrete-time systems. It is demonstrated theoretically on the affine class. A nonlinear simulation example is also provided to validate theoretical development.

Combining ERP systems with enterprise 2.0

The paper discusses both the complementary factors and contradictions of adoption ERP based systems with enterprise 2.0. ERP is well known as its' efficient business process management. Also the high failure rate the system implementation is famous as well. According to [1], ERP systems could achieve efficient business performance by enabling a standardized business process design, but at a cost of flexibility in operations. However, enterprise 2.0 supports flexible business process management, informal and less structured interactions [3],[4],[21]. Traditional researcher claimed efficiency and flexibility may seem incompatible in that they are different business objectives and may exist in different organizational environments. However, the paper will break traditional norms that combine ERP and enterprise 2.0 in a single enterprise to improve both efficient and flexible operations simultaneously. Based on the multiple cases studies, four cases presented different attitudes on usage ERP systems and enterprise social systems. Based on socio-technical theory, the paper presents in-depth analysis benefits of combination ERP with enterprise 2.0 for these firms.