# 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»

• ### Intelligent control for autonomous vehicles using real-time adaptive associative memory neural networks

Publication Year: 1991, Page(s):144 - 148
Cited by:  Papers (1)
| |PDF (288 KB)

Addresses the problem of adaptively controlling an autonomous vehicle. The plant is a complex, nonlinear function of many parameters, some of which will be time varying (e.g. vehicle mass), and operating in a dynamic environment (e.g. varying tyre/road friction coefficient). A priori modelling is a very time consuming and complex process, so a real-time, nonlinear adaptive algorithm is required wh... View full abstract»

• ### BARTIN: a neural structure that learns to take Bayesian minimum risk decisions

Publication Year: 1991, Page(s):14 - 18
Cited by:  Papers (1)
| |PDF (332 KB)

BARTIN (Bayesian real time networks) is a general structure for learning Bayesian minimum risk (maximum expected utility) decision schemes. It can be realized in a great variety of forms. The features that distinguish it from a standard Bayesian minimum risk classifier are, (i) it implements a general method for incorporating a prior distribution, and (ii) its ability to learn a risk minimising de... View full abstract»

• ### Robot control using the feedback-error-learning rule with variable feedback gain

Publication Year: 1991, Page(s):139 - 143
Cited by:  Papers (3)
| |PDF (284 KB)

A problem plaguing the application of neural networks in all fields is the difficulty of incorporating prior information to constrain the possible functions that the network can represent. This problem is addressed and solved in a robot control application. The authors present the numerical results of extensive simulations where the main interest is to investigate the generalization ability of the... 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»

• ### Neural classification of chest pain symptoms: a comparative study

Publication Year: 1991, Page(s):200 - 204
Cited by:  Papers (1)
| |PDF (320 KB)

The authors demonstrate the effectiveness of neural networks in the diagnosis of heart attacks (acute myocardial infarction). Two neural network classifiers are compared. The multi-layered Perceptron is found to perform well but the probabilistic interpretation of its output is not well defined. The Boltzmann Perceptron Classifier is found to have comparable performance and has the advantage that ... View full abstract»

• ### Visual surface of postal codes by neural networks using human examples

Publication Year: 1991, Page(s):364 - 368
| |PDF (344 KB)

The paper discusses the utilization of human visual search and describes the guidelines and implementation of a software capable to provide an environment where human beings generate examples of visual postal codes searches. It also explains how relevant information is extracted and presents the neural network-based system designed to use it View full abstract»

• ### A direct control method for a class of nonlinear systems using neural networks

Publication Year: 1991, Page(s):134 - 138
Cited by:  Papers (7)
| |PDF (304 KB)

Presents a direct control scheme for a class of continuous time nonlinear systems that are linear in the control variable. The objective of control is to track a desired reference signal. This type of system is encountered in many applications, e.g. rigid link robot manipulator control. The advantage of restricting attention to these systems is that the control theory of these systems is well deve... View full abstract»

• ### A rule-based dynamic back-propagation (DBP) network

Publication Year: 1991, Page(s):170 - 174
| |PDF (292 KB)

The paper presents and explains experiments performed on a neural network paradigm which works on the Back-Propagation (BP) formula together with additional rules for modifying the net structure. The function of the rules is to control the number of hidden units and their interconnections of a BP net. Hence, the net is capable of evolving' into the optimal topology itself without interference fro... 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»

• ### 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»

• ### Simulations of cardiac arrhythmias based on dynamical interactions between neural models of cardiac pacemakers

Publication Year: 1991, Page(s):195 - 199
| |PDF (320 KB)

An artificial neural network model of the cardiac conduction system is proposed. The dynamical behaviour of the model is used to simulate interactions between cardiac rhythm generating elements (pacemakers). The synchronization phenomenon of the heart pacemakers, underlying the normal heart rhythm, is demonstrated. Also, for abnormal conditions, obtained results suggest that the development of par... View full abstract»

• ### An analysis of self-organising networks based on goal-seeking neurons

Publication Year: 1991, Page(s):257 - 261
| |PDF (272 KB)

The principle involved in applying self-organising architectures to pattern recognition problems is that patterns which share common features are clustered together, with each cluster representing one and only one class. One architecture that follows such a principle is the GSN self-organising architecture (GSN8) a Boolean neural network proposed by Filho, Fairhurst and Bisset (1990, 19... View full abstract»

• ### A frame based implementation architecture for neural networks

Publication Year: 1991, Page(s):54 - 58
| |PDF (244 KB)

Neural networks have the potential to provide very cost effective pattern recognition machines provided that suitable hardware implementations can be found. The applicability of common neural network structures, such as the multi-layer feed-forward network, to different pattern recognition problems means that any particular implementation scheme will be widely applicable. This generality makes it ... View full abstract»

• ### Automatic signalized point recognition with feed-forward neural network

Publication Year: 1991, Page(s):359 - 363
| |PDF (500 KB)

The recognition and accurate location of specific patterns, such as of special targets or signalized points in digital images, is an important step in photogrammetric measurement procedures. This paper explores the capability of the feed-forward neural network using a version of back-propagation training for the recognition of targets that appear in digitized images of aerial photographs. These ta... View full abstract»

• ### On temporal sequence storage

Publication Year: 1991, Page(s):129 - 133
| |PDF (316 KB)

Presents a theoretical analysis and a series of simulations of a method for temporal sequence storage. The method is based on the power of leaky integrator neurons to store previous inputs over a range of times in the past. The theory and simulations presented here agree for the particular training rule which is of the simplest kind: to train the output so as to look as close as possible like the ... View full abstract»

• ### Applications of artificial neural networks to reverse software engineering

Publication Year: 1991, Page(s):163 - 169
| |PDF (468 KB)

In this paper a system has been described that has been used to explore the application of ANN based technology to reverse software engineering (RSE). The demonstrator system has been trained to identify complex sort algorithms within large real world' COBOL source listings. The ease with which the system can be extended, by training further neural networks to identify new algorithmic structures,... View full abstract»

• ### On the geometry of feedforward neural network weight spaces

Publication Year: 1991, Page(s):1 - 4
Cited by:  Papers (3)
| |PDF (220 KB)

As is well known, many feedforward neural network architectures have the property that their overall input-output function is unchanged by certain weight permutations and sign flips. The existence of these properties implies that if a global optimum of the network performance surface exists at some finite weight vector position, then many copies of a global minimum can be generated by geometric we... View full abstract»

• ### A fully integrated hand-printed character recognition system using artificial neural networks

Publication Year: 1991, Page(s):219 - 223
| |PDF (408 KB)

The paper presents an integrated strategy for hand-printed optical character recognition. A novel image processing algorithm is proposed that enhances the low frequency features of the input data. Logical neural networks are employed to classify the data. It is recognised that the classification performance will not be error-free due to ambiguities in the data, which cannot be resolved by human in... View full abstract»

• ### The neural control of locomotion in a quadrupedal robot

Publication Year: 1991, Page(s):333 - 335
Cited by:  Papers (2)
| |PDF (232 KB)

The authors consider whether there is any essential functional difference between the neural control systems involved in instinctive and learned walking. Is there incomplete overlap between the solutions accessible to evolutionary methods (or their synthetic counterparts, genetic algorithms) and those which can be reached by learning methods (or their synthetic counterparts, such as back propagati... View full abstract»

• ### Error recovery behaviour of feedback RAM-networks

Publication Year: 1991, Page(s):304 - 308
Cited by:  Papers (1)
| |PDF (252 KB)

Presents an analysis of the dynamics involved in the process of error recovery in Boolean neural nets with feedback loops. The main objective of the work is to show the conditions under which a randomly generated RAM-network recovers from input and state errors. RAM-nets of the type mentioned tend to have some inherent stability with respect to its input sequence. The approach adopted here is a pr... 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»

• ### Using a-priori information in networks

Publication Year: 1991, Page(s):242 - 246
Cited by:  Papers (2)
| |PDF (296 KB)

For control and supervision of dynamic systems, accurate prediction of the outputs and states is important. In the paper a new method is presented for prediction in the case where no, or only an inaccurate, model of the system is available. A feedforward neural network is useful in accurately predicting the output of systems for which a low-order input-output mapping exists. Different feedback con... View full abstract»

• ### Neural processing of airborne sonar for mobile robot applications

Publication Year: 1991, Page(s):267 - 270
Cited by:  Papers (1)
| |PDF (252 KB)

Describes a range of neural signal processing methods employed for B-Scan ultrasonic image enhancement and material identification. All approaches assume no a-priori knowledge of the environment. A Multi-Layered Perceptron (MLP) employing back propagation learning was used for all aspects of this research. The motivation for this work arises from a requirement to map and navigate within, hazardous... View full abstract»