Learning soft computing control strategies in a modular neural network architecture

Modelling and control of nonlinear dynamical systems is a challenging problem since the dynamics of such systems change over their parameter space. Conventional methodologies for designing nonlinear control laws, such as gain scheduling, are effective because the designer partitions the overall complex control into a number of simpler sub-tasks. This paper describes a new genetic algorithm based method for the design of a modular neural network (MNN) control architecture that learns such partitions of an overall complex control task. Here a chromosome represents both the structure and parameters of an individual neural network in the MNN controller and a hierarchical fuzzy approach is used to select the chromosomes required to accomplish a given control task. This new strategy is applied to the end-point tracking of a single-link flexible manipulator modelled from experimental data. Results show that the MNN controller is simple to design and produces superior performance compared to a single neural network (SNN) controller which is theoretically capable of achieving the desired trajectory. (C) 2003 Elsevier Ltd. All rights reserved.

Improving neural network training solutions using regularisation

This paper describes the application of regularisation to the training of feedforward neural networks, as a means of improving the quality of solutions obtained. The basic principles of regularisation theory are outlined for both linear and nonlinear training and then extended to cover a new hybrid training algorithm for feedforward neural networks recently proposed by the authors. The concept of functional regularisation is also introduced and discussed in relation to MLP and RBF networks. The tendency for the hybrid training algorithm and many linear optimisation strategies to generate large magnitude weight solutions when applied to ill-conditioned neural paradigms is illustrated graphically and reasoned analytically. While such weight solutions do not generally result in poor fits, it is argued that they could be subject to numerical instability and are therefore undesirable. Using an illustrative example it is shown that, as well as being beneficial from a generalisation perspective, regularisation also provides a means for controlling the magnitude of solutions. (C) 2001 Elsevier Science B.V. All rights reserved.

System oriented neural networks - Problem formulation, methodology and application

A novel methodology is proposed for the development of neural network models for complex engineering systems exhibiting nonlinearity. This method performs neural network modeling by first establishing some fundamental nonlinear functions from a priori engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural network model best fitting the system data. The objective is to improve the transparency of the neural networks, i.e. to produce physically meaningful

Microscopical evaluation of neural connectivity between paired stages of Eudiplozoon nipponicum (Monogenea : Diplozoidae)

Diplozoidae monogeneans are fish-gill ectoparasites comprising 2 individuals fused in so-called permanent copula. This unique situation occurs when 2 larvae (diporpae) make contact on the host gill, such that their union triggers maturation into an individual adult worm. The present study examined paired stages of Eudiplozoon nipponicum microscopically to ascertain whether somatic fusion involves neural connectivity between these 2 heterogenic larvae. Neuronal pathways were demonstrated in whole-mount preparations of the worm, using indirect immunocytochemical techniques interfaced with confocal scanning laser microscopy for peptidergic and serotoninergic innervations and enzyme cytochemical methodology and light microscopy for cholinergic components. Elements of the central nervous systems of paired worms are connected by commissures the region of fusion so that the 2 systems are in structural continuity. Interindividual connections were most apparent between corresponding ventral nerve cords. All 3 classes of neuronal mediators were identified throughout both central and peripheral connections of the 2 nervous systems. The anatomical complexity and apparent plasticity of the diplozoon nervous system suggest that it has a pivotal role not only in motility, feeding, and reproductive behaviors but also in the events of larval pairing and somatic fusion.