# 1991 Second International Conference on Artificial Neural Networks

## Filter Results

Displaying Results 1 - 25 of 82
• ### Homotopy continuation method for neural networks

Publication Year: 1991, Page(s):19 - 23
Cited by:  Papers (5)
| | PDF (234 KB)

This paper proposes the use of homotopy continuation method for training the neural networks. Homotopy methods have been demonstrated to be superior to gradient descent methods in many applications such as nonlinear optimization problems, mathematical analysis, and more recently, signal processing. The power of these methods lies in their ability to provide globally convergent solutions, and under... View full abstract»

• ### Operational fault tolerance of the ADAM neural network system

Publication Year: 1991, Page(s):285 - 289
Cited by:  Papers (1)
| | PDF (469 KB)

Neural networks offer a powerful parallel distributed computational system which can be trained to solve many problems. They also appear to be inherently fault tolerant. This is unlike a conventional computing system where fault tolerance is achieved by redundancy, thus increasing its overall complexity. The fault tolerance of the advanced distributed associative memory neural network (ADAM) is in... View full abstract»

• ### Learning temporal structures by continuous backpropagation

Publication Year: 1991, Page(s):124 - 128
| | PDF (320 KB)

The learning of temporal structures, e.g. limit cycles, by recurrent neural networks has recently received considerable attention. Unfortunately, some of the algorithms proposed so far are of high storage complexity. Others, being extensions of the Hopfield model, have quite limited storage capacity. Generalizing the work of Doya and Yoshizawa (1989) as well as Urbanczik (1990), the author derives... View full abstract»

• ### Artificial neural network based multivariable predictive control

Publication Year: 1991, Page(s):119 - 123
Cited by:  Papers (2)
| | PDF (312 KB)

Considers the development of dynamic process models using artificial neural networks. Two alternative network modelling philosophies are considered; a time series approach and imbedded dynamics within the network structure. Both methods are shown to be suitable approaches to dynamic modelling, given due consideration to the methodologies of training. With process dynamics captured in the artificia... View full abstract»

• ### Experience in using neural networks for electronic diagnosis

Publication Year: 1991, Page(s):115 - 118
Cited by:  Papers (5)  |  Patents (3)
| | PDF (244 KB)

British Telecommunication plc (BT) has an interest in developing fast, efficient diagnostic systems especially for high volume circuit boards as found in today's digital telephone exchanges. Previous work to produce a diagnostic system for line cards has shown that a model-based, expert system shell can be most beneficial in assisting in the diagnosis and subsequent repair of these complex, mixed-... View full abstract»

• ### A statistical investigation of cost-function derivatives for neural networks with continuous activation functions

Publication Year: 1991, Page(s):34 - 38
| | PDF (256 KB)

By making simple assumptions on the distribution of potentials at the nodes of a feed-forward multilayer network with continuous activation functions the author derives analytic expressions for the mean and standard deviation of the values of the cost function and root-mean-square values of its derivatives. He shows how this information can be used to obtain systematic estimates of the range of we... View full abstract»

• ### Artificial neural networks in forecasting minimum temperature [weather]

Publication Year: 1991, Page(s):112 - 114
Cited by:  Papers (1)
| | PDF (204 KB)

Forecasting the minimum temperature (Tmin) is one of the most important operational practices carried out by Meteorological Services worldwide. In tackling the problem of the minimum temperature forecasting using artificial neural networks, the authors use raw data extracted from the synoptic meteorological observations recorded at three-hour intervals at Larnaca Airport, Cyprus (34°... View full abstract»

• ### On the iterative inversion of RBF networks: a statistical interpretation

Publication Year: 1991, Page(s):29 - 33
Cited by:  Papers (3)
| | PDF (316 KB)

The method of the inversion of arbitrary continuous multilayer networks is extended to the class of radial basis function networks. The problem centres around how to obtain an input pattern (or set of patterns) which has an associated network output which is close (in a least squares sense) to a desired target pattern. Why this nonlinear inverse problem is of interest is discussed and the action o... View full abstract»

• ### Pattern recognition in position sensitive γ-ray detectors

Publication Year: 1991, Page(s):107 - 111
| | PDF (256 KB)

The NASA/ESA International Gamma-Ray Astrophysics Laboratory (INTEGRAL) γ-ray telescope satellite will use novel 3-dimensional readout position detectors and energy sensitive photon detectors. Their complexity means that significantly more raw data are generated than can be sent by conventional telemetry channels from satellite to Earth ground stations. The authors present the preliminary re... View full abstract»

• ### Neural network based current controller for HVDC transmission systems

Publication Year: 1991, Page(s):373 - 378
Cited by:  Papers (2)
| | PDF (304 KB)

The paper presents a neural network (NM) based current controller for a rectifier in a two-terminal HVDC back-to-back tie. This controller adapts its gain parameters to provide better or similar recovery dynamics when compared to the more traditional PI current controller. Comparisons between the proposed NN and traditional PI controller responses are provided by means of results obtained from dig... View full abstract»

• ### HPS signals detection using neural network adaptive filter

Publication Year: 1991, Page(s):234 - 236
| | PDF (132 KB)

The recent research in HPS signal detection has focused on beat-to-beat measurement. Most of the applied methods rely on linear adaptive filters. In the paper the use of nonlinear adaptive filters based on a recurrent neural network is proposed. Two training algorithms are briefly described View full abstract»

• ### Adaptive equalization using the lp back propagation algorithm

Publication Year: 1991, Page(s):10 - 13
| | PDF (164 KB)

This paper discusses the performance of adaptive equalization using lp, 1<p⩽2, back propagation algorithm. The results indicate that as p decreases, the convergence time tends to reduce roughly linearly. Considerable improvement in the rate of convergence and bit error rate performance for 1<p<2 over p=2, has been shown to be fea... View full abstract»

• ### Further developments of a neural network speech fundamental period estimation algorithm

Publication Year: 1991, Page(s):340 - 344
| | PDF (300 KB)

This work describes a speech fundamental period estimation algorithm that estimates the time of excitation of the vocal tract using a pattern classifier, the multi-layer perceptron (MLP). The pattern classifier was trained using speech semi-automatically labelled by means of an algorithm that makes use of the output from a Laryngograph. Various issues arising in the training of the system were exp... View full abstract»

• ### Parallel trials versus single search in supervised learning

Publication Year: 1991, Page(s):24 - 28
| | PDF (256 KB)

The comparison between parallel trials and single search in supervised learning is approached by introducing an appropriate formalism based on random variables theory. The fundamental role played by the probability P(t) that an optimization algorithm converges in the interval [0,t] is thus emphasized. The work is divided in two parts: in the first one some basic theorems are show... View full abstract»

• ### Multicriterion neural network optimization approach to image reconstruction from projections

Publication Year: 1991, Page(s):103 - 106
| | PDF (204 KB)

A multicriterion optimization based neural model with application to image reconstruction from projections is proposed. The reconstruction procedure consists of two stages: estimation of the parameters of the neural network model and image reconstruction. Computer simulation results showed that the novel method is very efficient View full abstract»

• ### Fast algorithms to find invariant features for a word recognizing neural net

Publication Year: 1991, Page(s):180 - 184
Cited by:  Papers (1)
| | PDF (284 KB)

A short description of the feature finding neural net (FFNN) for the recognition of isolated words will be given. As has been shown elsewhere, during recognition mode FFNN is faster than the classical HMM and DTW recognizers and yields similar recognition rates. In this article the emphasis is placed on optimal and fast algorithms for selecting relevant features from the speech signal. By the grow... View full abstract»

• ### A back propagation network as a decision aid in flexible welding system design

Publication Year: 1991, Page(s):271 - 275
| | PDF (304 KB)

A neural network has been applied to a new classification and coding system, a sub-set of Group Technology. The new code matches welding processing requirements of components with the features of a flexible welding cell. This work forms part of the development of a new method of flexible manufacturing systems design. The emphasis of the paper is coding the inputs and outputs of the network, and th... View full abstract»

• ### Encoding temporal structure in probabilistic RAM nets

Publication Year: 1991, Page(s):369 - 372
Cited by:  Papers (4)
| | PDF (272 KB)

The authors show how both gradient descent and reinforcement training can be used to teach a recurrent probabilistic RAM (pRAM) net to classify binary strings of arbitrary length, and how a form of reinforcement training can be used with leaky integrator' pRAM nodes to enable them to store complex temporal sequences View full abstract»

• ### Normalised hierarchical data structures for automatic target recognition

Publication Year: 1991, Page(s):229 - 233
| | PDF (320 KB)

A new method is presented that involves teaching an artificial neural network (advanced distributed associative memory ADAM) with a number of synthetic images resulting from a hierarchical data structure descriptor that characterises an object's 3D volume. The method results in a highly accurate recognition process that significantly reduces the duration of a generally time consuming training proc... View full abstract»

• ### A high order feedback net (HOFNET) with variable non-linearity

Publication Year: 1991, Page(s):59 - 63
| | PDF (196 KB)

Most neural networks proposed for pattern recognition sample the incoming image at one instant and then analyse it. This means that the data to be analysed is limited to that containing the noise present at one instant. Time independent noise is therefore, captured but only one sample of time dependent noise is included in the analysis. If however, the incoming image is sampled at several instants... View full abstract»

• ### Motion perception and recognition using moving light displays

Publication Year: 1991, Page(s):91 - 94
| | PDF (192 KB)

Despite the limited amount of information that is available to the observer of a moving light display, humans are able to infer detailed information about the activity and identity of the actors within the film. The development of a system, which uses such displays to recognise different types of human motion, is described using a spatio-temporal neural network to classify different temporal seque... View full abstract»

• ### Self-supervised training of hierarchical vector quantisers

Publication Year: 1991, Page(s):5 - 9
Cited by:  Papers (1)
| | PDF (316 KB)

The author has previously developed a hierarchical vector quantisation (VQ) model which successfully applied to time series and image compression respectively. The paper derives an extension to this model, in which the author backpropagates signals from higher to lower layers of the hierarchy to self-supervise the training of the VQ. He reviews the basic properties of his VQ model and its relation... View full abstract»

• ### Estimation and neurocontrol in the presence of feedback

Publication Year: 1991, Page(s):300 - 303
| | PDF (228 KB)

When feedforward adaptive control is applied to distributed parameter plants a feedback path often exists around the controller. This feedback path introduces a potential instability and greatly changes the behaviour of the controlled system, usually degrading performance with respect to the no feedback' case. The feedback induced effects present in feedforward neurocontrol are similar to those e... View full abstract»

• ### Orthogonal least squares algorithm for training multi-output radial basis function networks

Publication Year: 1991, Page(s):336 - 339
Cited by:  Papers (2)  |  Patents (1)
| | PDF (184 KB)

The radial basis function (RBF) network offers a viable alternative to the two-layer neural network in many signal processing applications. A novel learning algorithm for RBF networks (S. Chen et al., 1990, 1991) has been derived based on the orthogonal least squares (OLS) method operating in a forward regression manner (Chen et al., 1989). This is a rational way to choose RBF centres from data po... View full abstract»

• ### Dynamic coupling weights in a neural network system

Publication Year: 1991, Page(s):350 - 353
| | PDF (164 KB)

A number of applications of Neural Network Systems (NNS) for speech signal processing have been developed, Kohonen (1988), Wu, Warwick and Koska (1990), Wu and Warwick (1990). The concept of feature maps makes the display of phoneme recognition result directly from the output of a NN System in the form of a two-dimensional map. Chinese phoneme feature maps have also been tested in a similarly stru... View full abstract»