Input/output linearization using dynamic recurrent neural networks

This paper brings together two areas of research that have received considerable attention during the last years, namely feedback linearization and neural networks. A proposition that guarantees the Input/Output (I/O) linearization of nonlinear control affine systems with Dynamic Recurrent Neural Networks (DRNNs) is formulated and proved. The proposition and the linearization procedure are illustrated with the simulation of a single link manipulator.

Neural networks for linear control: an analysis

This paper considers the use of radial basis function and multi-layer perceptron networks for linear or linearizable, adaptive feedback control schemes in a discrete-time environment. A close look is taken at the model structure selected and the extent of the resulting parameterization. A comparison is made with standard, nonneural network algorithms, e.g. self-tuning control.

Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.

Dynamic recurrent neural network for system identification and control

A dynamic recurrent neural network (DRNN) that can be viewed as a generalisation of the Hopfield neural network is proposed to identify and control a class of control affine systems. In this approach, the identified network is used in the context of the differential geometric control to synthesise a state feedback that cancels the nonlinear terms of the plant yielding a linear plant which can then be controlled using a standard PID controller.

Neural networks for power systems alarm handling

A multi-layered architecture of self-organizing neural networks is being developed as part of an intelligent alarm processor to analyse a stream of power grid fault messages and provide a suggested diagnosis of the fault location. Feedback concerning the accuracy of the diagnosis is provided by an object-oriented grid simulator which acts as an external supervisor to the learning system. The utilization of artificial neural networks within this environment should result in a powerful generic alarm processor which will not require extensive training by a human expert to produce accurate results.

Neural network feature maps for Chinese phonemes

It has been shown through a number of experiments that neural networks can be used for a phonetic typewriter. Algorithms can be looked on as producing self-organizing feature maps which correspond to phonemes. In the Chinese language the utterance of a Chinese character consists of a very simple string of Chinese phonemes. With this as a starting point, a neural network feature map for Chinese phonemes can be built up. In this paper, feature map structures for Chinese phonemes are discussed and tested. This research on a Chinese phonetic feature map is important both for Chinese speech recognition and for building a Chinese phonetic typewriter.

A critique of neural networks for discrete-time linear control

This paper discusses the use of multi-layer perceptron networks for linear or linearizable, adaptive feedback.control schemes in a discrete-time environment. A close look is taken at the model structure selected and the extent of the resulting parametrization. A comparison is made with standard, non-perceptron algorithms, e.g. self-tuning control, and it is shown how gross over-parametrization can occur in the neural network case. Because of the resultant heavy computational burden and poor controller convergence, a strong case is made against the use of neural networks for discrete-time linear control.

Bi-directional human machine interface via direct neural connection

This paper presents an application study into the use of a bi-directional link with the human nervous system by means of an implant, positioned through neurosurgery. Various applications are described including the interaction of neural signals with an articulated hand, a group of cooperative autonomous robots and to control the movement of a mobile platform. The microelectrode array implant itself is described in detail. Consideration is given to a wider range of possible robot mechanisms, which could interact with the human nervous system through the same technique.

Glycogen synthase kinases 3α and 3β in cardiac myocytes: regulation and consequences of their inhibition

Inhibition of glycogen synthase kinase 3β (GSK3β) as a consequence of its phosphorylation by protein kinase B/Akt (PKB/Akt) has been implicated in cardiac myocyte hypertrophy in response to endothelin-1 or phenylephrine. We examined the regulation of GSK3α (which we show to constitute a significant proportion of the myocyte GSK3 pool) and GSK3β in cardiac myocytes. Although endothelin increases phosphorylation of GSK3 and decreases its activity, the response is less than that induced by insulin (which does not promote cardiac myocyte hypertrophy). GSK3 phosphorylation induced by endothelin requires signalling through the extracellular signal-regulated kinase 1/2 (ERK1/2) cascade and not the PKB/Akt pathway, whereas the reverse is true for insulin. Cardiac myocyte hypertrophy involves changes in morphology, and in gene and protein expression. The potent GSK3 inhibitor 1-azakenpaullone increases myocyte area as a consequence of increased cell length whereas phenylephrine increases both length and width. Azakenpaullone or insulin promotes AP1 transcription factor binding to an AP1 consensus oligonucleotide, but this was significantly less than that induced by endothelin and derived principally from increased binding of JunB protein, the expression of which was increased. Azakenpaullone promotes significant changes in gene expression (assessed by Affymetrix microarrays), but the overall response is less than with endothelin and there is little overlap between the genes identified. Thus, although GSK3 may contribute to cardiac myocyte hypertrophy in some respects (and presumably plays an important role in myocyte metabolism), it does not appear to contribute as significantly to the response induced by endothelin as has been maintained.