By Topic

Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand International Two-Stream Conference on

Date 24-26 Nov. 1993

Filter Results

Displaying Results 1 - 25 of 95
  • 1993 First New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems

    Publication Year: 1993, Page(s): 0_1
    Request permission for commercial reuse | PDF file iconPDF (35 KB)
    Freely Available from IEEE
  • On neural networks for symbolic processing

    Publication Year: 1993, Page(s):5 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (148 KB)

    Existing approaches to integrating neural and symbolic processing are divided into the following four categories: developing specialized, structured, localist networks for symbolic processing; performing symbolic processing in distributed neural networks (in a holistic way); combining separate symbolic and neural network modules; and using neural networks as basic elements in symbolic architecture... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A learning scheme for bipartite recurrent networks and its performance

    Publication Year: 1993, Page(s):34 - 37
    Cited by:  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (344 KB)

    A new learning scheme specialized to recurrent neural networks with the bipartite topology is proposed. The scheme is expected to have better convergence than the general Boltzmann machine learning. This improvement results from the restricted form of the network topology and an energy form devised to have a dominant global minimum. Compared to the recurrent backpropagation algorithm, the scheme i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge capture model for expert systems development

    Publication Year: 1993, Page(s):163 - 164
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (152 KB)

    The development of expert systems requires the efficient capturing and organizing of diverse knowledge in a form suitable for encoding in an expert system shell. A knowledge capture model has been developed and applied for expertise in the selection and use of materials. Two expert systems are currently under development using the model: GeoMat on selection and use of materials for geothermal ener... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining engineering models with biophysical models to analyze a biological neural network: the electrosensory system of sharks, skates and rays

    Publication Year: 1993, Page(s):8 - 10
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (228 KB)

    The elasmobranch electrosensory system forms a neural representation of weak electrical field sources in the environment. Electrical noise correlated to the animal's own activity is rejected at an early stage of processing in the brain. The noise rejecting mechanism appears to be a neural analog of an adaptive array filter in the dorsal octavolateral nucleus of the medulla. The authors have applie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network encoding approach comparison: an empirical study

    Publication Year: 1993, Page(s):38 - 41
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    The authors report the results of an empirical study about the effect of input encoding on the performance of a neural network in the classification of numerical data. Two types of encoding schemes were studied, namely numerical encoding and bit pattern encoding. Fisher Iris data were used to evaluate the performance of various encoding approaches. It was found that encoding approaches affect a ne... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic modeling and control of nonlinear systems using neural network

    Publication Year: 1993, Page(s):327 - 330
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    The basic concept of design of dynamic neural controllers is discussed, emphasizing the control of the nonminimum phase plant. Neural networks are used to design a nonlinear controller combined with a robust linear controller. It unifies the nonlinear components in the controller and the plant together. This scheme simplifies the structure of the dynamic neural controller and modeling. Simulation ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Problems in expert systems development

    Publication Year: 1993, Page(s):166 - 167
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (144 KB)

    Summary form only given. The pitfalls of using prototyping and iteration in expert systems development are examined. It is argued that substituting prototyping for a thorough understanding of the process can cause many problems. Moreover, even when the analysis of expertise and the modeling of the domain are placed firmly within the framework of the life cycle, there are still problems with knowle... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bistability, noise, and information processing in sensory neurons

    Publication Year: 1993, Page(s):11 - 14
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (368 KB)

    The author considers the interpretation of time series data from firing events in periodically stimulated sensory neurons. A theoretical model, representing the neurons as bistable switching elements embedded in a Gaussian noise background, is considered. The cooperative effects arising through the coupling of the noise to the modulation are examined, together with their possible implications in t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for hybrid intelligent systems

    Publication Year: 1993, Page(s):206 - 209
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (348 KB)

    With the existing growth of information processing technology, there appear to be emerging two rival models of computation: one model spans conventional numeric and symbolic processing and the other the newer adaptive fuzzy forms of processing. With the realization that most complex real-world problems are not solvable by either model alone, there is great interest in combining the strengths of in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Practical polynomial expansion of input data can improve neurocomputing results

    Publication Year: 1993, Page(s):42 - 45
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (268 KB)

    Multi-layered perceptron (MLP) neurocomputing networks may be slow-learners and produce nonanalytical results; however, when presented with appropriately conditioned input data MLPs offer very good generalization results for complex classification problems. The author recounts some experiences from, and techniques used in, applying MLPs and backpropagation to find successful and better solutions t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solving four-colouring map problem using genetic algorithm

    Publication Year: 1993, Page(s):332 - 333
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB)

    The authors outline an approach to four-coloring of maps using a genetic algorithm. The objective of this map coloring problem is to shade each region of the map with a color such that no adjacent regions are of the same color. Simulation results show that the 48-region USA map problem can be solved on a PC platform within 400 generations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object-oriented development of expert systems

    Publication Year: 1993, Page(s):168 - 172
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    The authors outline and discuss the main issues involved when applying the object-oriented approach to expert systems development. They focus on their utilization in the analysis, design and implementation of a scholarship eligibility consultant expert system. An intelligent environment which provides assistance with scholarship applications is implemented. The object-oriented approach to knowledg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The chaotic self-organizing map

    Publication Year: 1993, Page(s):15 - 18
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB)

    A chaotic self-organizing map can be produced by replacing the linear neural units of the conventional self-organizing map with neural units capable of producing chaos. The introduction of chaos into the self-organizing map is shown to improve the ability of the network to cluster input patterns View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speech recognition based on Kohonen self-organizing feature maps and hybrid connectionist systems

    Publication Year: 1993, Page(s):113 - 117
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    Describes a series of experiments on using Kohonen self-organizing maps and hybrid systems for continuous speech recognition. Experiments with different nonlinear transformations on the signal before using a neural network has been done and results compared. The hybrid system developed by the authors combines self-organizing feature maps with dynamic time warping. The experiments suggest that the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An object-oriented hybrid environment for integrating neural networks and experts systems

    Publication Year: 1993, Page(s):210 - 213
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB)

    With the emerging realization that most complex real-world problems are difficult to solve by either symbolic or adaptive paradigms, there is great interest in combining the strengths of individual techniques (such as neural networks and expert systems), from these opposing forms of information processing. The object-oriented hybrid environment described allows the strengths of these contending pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using precepts to augment training set learning

    Publication Year: 1993, Page(s):46 - 51
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    The goal of learning systems is to generalize. Generalization is commonly based on the set of critical features the system has available. Training set learners typically extract critical features from a random set of examples. While this approach is attractive, it suffers from the exponential growth of the number of features to be searched. The authors propose to extend it by endowing the system w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The mind's eye: reconstructing noise corrupted objects, extracting secondary structure and figure ground separation

    Publication Year: 1993, Page(s):80 - 85
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB)

    The SLME network is a massively parallel recurrent, iterative, multiple constraint satisfaction neural network. It is capable of learning to solve problems including segmentation and vision tasks. It develops its own knowledge and feature set during iterative training. It consists of a retina of cells that learn their behavior and function during training. The cells are local processors that achie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Connectionist computations based on an optical thin-film model

    Publication Year: 1993, Page(s):130 - 133
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    An alternative connectionist architecture to the one based on the neuroanatomy of biological organisms is described. The proposed architecture is based on an optical thin-film multilayer model, with the thicknesses of thin-film layers serving as adjustable `weights' for the computation. The nature of the model, some examples, and optical implementation considerations are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distortion-invariant object recognition using adaptive resonance theory

    Publication Year: 1993, Page(s):341 - 344
    Cited by:  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    Classification and recognition of multiple objects under changes in position, orientation and scale are needed in practical applications such as automation of assembly lines. One of the main drawbacks in the conventional pattern recognition technique is the enormous time and computational overhead required for classification. However, the conventional techniques are well-suited for extracting the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Industrial application of fuzzy-neuro process monitoring system

    Publication Year: 1993, Page(s):298 - 299
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (100 KB)

    Condition monitoring of industrial processes is an excellent application area where fuzzy logic and neural networks are able to demonstrate its usefulness. In this article, we show that by taking a subjective approach towards statistical process control, a natural link exists between humans' analytic skill and statistical charts which are tools of formal quality control measures. The application o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using data mining to support the construction and maintenance of expert systems

    Publication Year: 1993, Page(s):156 - 159
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    Many expert systems are constructed from and allied with a large collection of databases that are continually being updated. The authors address the issues of how such a knowledge base can be constructed using tools that search the databases for significant, unexpected correlations and present them to the knowledge engineer for review. Once a knowledge base has been constructed, there is the probl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network based relaying scheme for distribution system high impedance fault detection

    Publication Year: 1993, Page(s):321 - 324
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    The authors present an artificial neural network (ANN)-FFT based novel detection scheme for high impedance faults (HIFs) in electrical distribution networks. The scheme uses an ANN and utilizes a discriminant vector of dominant harmonic sequence magnitudes of negative and zero (-, 0) components of the supply voltages and currents at the substation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A task oriented intelligent tutoring system

    Publication Year: 1993, Page(s):196 - 200
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    The authors present an intelligent tutoring system for a sonar application. The system provides assistance to the student that supports a rich learning interaction and that provides online control of student progress. Providing guidance to learners is an area where AI researchers and computer based training (CBT) researchers can both make vital contributions. The authors have used both technologie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An application of neural networks to emulation of aesthetic judgements

    Publication Year: 1993, Page(s):334 - 337
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    Models of perception of abstract black and white images are proposed. The core part of the models are artificial neural networks (ANNs). The computer system is trained by providing samples of pictures and some pre-calculated characteristics. Once successfully trained, the system is able to classify new pictures displaying aesthetic preferences similar to those owned by its teachers View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.