By Topic

Artificial Neural Networks and Expert Systems, 1995. Proceedings., Second New Zealand International Two-Stream Conference on

Date 20-23 Nov. 1995

Filter Results

Displaying Results 1 - 25 of 93
  • Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems

    Publication Year: 1995
    Request permission for commercial reuse | PDF file iconPDF (635 KB)
    Freely Available from IEEE
  • Emulating fuzzy mappings with a neural network architecture

    Publication Year: 1995, Page(s):251 - 254
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (259 KB)

    We propose a neural network model for the processing of fuzzy data. The network parameters (weights) are standard real numbers and the spreads at the output level result exclusively from uncertainty in the input data. Our network model performs 'intelligent' inference calculations on the basis of fuzzy data and minimizes uncertainty in the final output. The number of free parameters (weights) in o... View full abstract»

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

    Publication Year: 1995
    Request permission for commercial reuse | PDF file iconPDF (126 KB)
    Freely Available from IEEE
  • Fuzzy logic in DBMSs and querying

    Publication Year: 1995, Page(s):106 - 109
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (408 KB)

    We briefly survey main developments and issues related to the use of (broadly perceived) fuzzy logic in database management systems (DBMSs), in particular in database querying. We show how this can help make DBMSs and their usage easier and more human-consistent View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy logic and its hardware implementation

    Publication Year: 1995, Page(s):102 - 105
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    The fundamentals of a fuzzy logic circuit and its application to fuzzy inference chips and fuzzy flip flops are mentioned with circuit examples View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modelling human cognition: a singular task

    Publication Year: 1995
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (56 KB)

    Summary form only given. The cognitive literature has debated at some length the rival merits of models in which there are associationist connections and implicit rules and models in which there are explicit, syntactically structured rules. Human cognition represents a singular challenge to both models for reasons that only emerge when we undertake an analysis of the nature of human cognitive adap... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Indicators of hidden neuron functionality: the weight matrix versus neuron behaviour

    Publication Year: 1995, Page(s):26 - 29
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (316 KB)

    Pruning of redundant or less important hidden neurons from the popular backpropagation trained neural networks is useful for a host of reasons, ranging from improvements of generalisation performance, to use as a precursor for rule extraction. For pruning it is necessary to identify hidden neurons with similar functionality. We have previously used a pruning process based on the behaviour of the h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Radar pulse train parameter estimation and tracking using neural networks

    Publication Year: 1995, Page(s):95 - 98
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB)

    The post-deinterleaving radar pulse train problem requires estimation of the parameters and tracking of the individual pulse trains. A simple recurrent backpropagation neural network is used based on a simple state space time series formulation of the radar problem. The network incorporates a novel heuristic adaptive error threshold that allows simultaneously good tracking and parameter estimating... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fuzzy expert system for hierarchical placement of parts on printed circuit board

    Publication Year: 1995, Page(s):342 - 345
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (284 KB)

    For computer aided design (CAD)/design automation (DA) for printed circuit board (PCB), automatic placement of parts has been a difficult problem. For realizing good placement, not only the structures but also the functions of the circuit should be grasped and some hierarchical methods for the placement should be done. This paper presents a new hierarchical method of placement of parts on the PCB ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On performance measures of artificial neural networks trained by structural learning algorithms

    Publication Year: 1995, Page(s):22 - 25
    Cited by:  Papers (315)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (408 KB)

    Structural learning in multi layer, feedforward neural networks was studied using M. Ishikawa's (1994) modified backpropagation algorithm with forgetting of the connection weights. The proper choice of forgetting constant was investigated previously but no generally accepted method has been established yet. The generalization rate of the trained network is analyzed as a possible means of selecting... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • NN classifiers: reducing the computational cost of cross-validation by active pattern selection

    Publication Year: 1995, Page(s):91 - 94
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    We propose a new approach for leave-one-out cross-validation of neural network classifiers called “cross-validation with active pattern selection” (CV/APS). In CV/APS, the contribution of the training patterns to backpropagation learning is estimated and this information is used for active selection of CV patterns. On two artificial examples, the computational cost of CV can be reduced... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research activities on spontaneous speech translation

    Publication Year: 1995, Page(s):280 - 283
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    In the coming 21st century, “global communication among different languages” will become more promising and more realistic. However, despite the great expectations of society for such an ideal speech translating system, there remains a great number of difficult problems related to acoustic and linguistic phenomena that need to be overcome. This is because spoken language is characteriz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A mechanism for the development of feature detecting neurons

    Publication Year: 1995, Page(s):59 - 62
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    The mammalian retina and visual cortex contain feature detecting neurons with a remarkable similarity to neurons in artificial neural networks for principal component analysis. Hebbian-type learning is one of the mechanisms responsible for the development of such neurons. It does not model, however, control of the number of neurons that develop in response to input. We propose a mechanism that ada... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimal qualitative topologic world models for mobile robot

    Publication Year: 1995, Page(s):338 - 341
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    World models for mobile robots as introduced in many projects, are mostly redundant regarding similar situations detected in different places. The present paper proposes a method for dynamic generation of a minimal world model based on these redundancies. The technique is an extention of the qualitative topologic world modelling methods. As a central aspect the reliability regarding error-toleranc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study of chaos neural network with a periodic activation function

    Publication Year: 1995, Page(s):45 - 50
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    We put forward a novel chaos neuron model and investigate its dynamic properties. The artificial neuron model is defined by such periodic input-output mapping as a sinusoidal function. It is obviously shown that the present neural network has the ability of embedded pattern retrieval in the neural network beyond the conventional one with a monotonous mapping such as the signum function. This advan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An emotion processing system based on fuzzy inference and subjective observations

    Publication Year: 1995, Page(s):15 - 20
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB)

    The two theories concerning mixed emotions, adopted in this research is briefly explained. Also discussed are the image codes linked to the mixed emotional words and the way to realize a mechanism using fuzzy inference, in which the internal emotion of a simulated person reacts on a sequence of inputted terms and evokes some emotional change. The relevant part of the theory for subjective observat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network that learns to play five-in-a-row

    Publication Year: 1995, Page(s):87 - 90
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    A neural network that learns to play the board game of five-in-a-row is presented. The basic idea of the approach is to let an appropriately designed network play a series of games against an opponent and use a reinforcement learning algorithm to train the network to evaluate the non-occupied board positions by rewarding good moves and penalizing bad moves. The performance of the proposed network ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The development of the Otago speech database

    Publication Year: 1995, Page(s):298 - 301
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    A collection of digits and words, spoken with a New Zealand English accent, has been systematically and formally collected. This collection along with the beginning and end points of the realised phonemes from within the words, comprise the Otago Speech Corpora. A relational database management system has been developed to house the speech data. This system provides much more usability, flexibilit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deriving baseline detection algorithms from verbal descriptions

    Publication Year: 1995, Page(s):247 - 250
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB)

    The presented strategy of automatic baseline detection in chromatograms combines fuzzy logic and neural network approaches. It is based on a verbal description of a baseline referring to a 2D image of a chromatogram instead of a data vector. Baselines are expected to touch data points on the lower border of the chromatogram forming a mainly horizontal and straight line. That description has been t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Heuristics for solving fuzzy constraint satisfaction problems

    Publication Year: 1995, Page(s):132 - 135
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    Work in the field of AI over the past twenty years has shown that many problems can be represented as constraint satisfaction problems and efficiently solved by constraint satisfaction algorithms. However, constraint satisfaction in its pure form isn't always suitable far real world problems, as they often tend to be inconsistent, which means the corresponding constraint satisfaction problems don'... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An architecture for understanding human instructions, learning, and planning

    Publication Year: 1995, Page(s):231 - 234
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    This paper presents our ongoing work in building an architecture for instructable systems, along with an illustrative example. The architecture uses knowledge about instruction discourse, planning and induction, to create a task representation that is suitable for execution as well as for planning later tasks. Major components have been built; future work includes putting them together. Our aim is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards a model of multi-agent connectionist hybrid system

    Publication Year: 1995, Page(s):273 - 276
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    A connectionist system that is capable of reasoning about problems posed usually to expert systems is used for the purpose of dynamic cognition tasks. The architecture of such a system must contain “classical” AI representations and symbolic information processing entities. Coupling this part of the system with multiple connectionist structures implies a definition for the intercommuni... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A wool specification expert system in LEVEL5 Object or experiences of a procedural programmer with a hybrid system

    Publication Year: 1995, Page(s):393 - 395
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (176 KB)

    Some experiences of a self-trained programmer developing an expert system (ES), initially in VP Expert and then ported to LEVEL5 Object, are discussed. Moving from an incremental approach of developing code in FORTRAN to the disciplined approach required for an ES which is object oriented (OO), proved frustrating but also rewarding. A need for careful analysis and design not only provided a struct... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experience in developing models of industrial plants by large scale artificial neural networks

    Publication Year: 1995, Page(s):326 - 329
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (288 KB)

    Artificial neural networks (ANN) are used for modeling of industrial processes. However, most of the published papers deal with small or medium scale systems. One of the possible reasons, the slow learning or non convergence of large scale networks can now be overcome by the use of non-developed ANN process model may be optimized, after the elimination of non-relevant input and hidden-layer &ldquo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach to design fuzzy IF-THEN rules for fuzzy-controlled static VAr compensator

    Publication Year: 1995, Page(s):116 - 119
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    The paper describes an approach to design fuzzy IF-THEN rules for the fuzzy-controlled static VAr compensator (FCSVC) in a three-phase electric power system. In general, designing fuzzy IF-THEN rules for fuzzy-controlled non-linear MIMO systems is very difficult because the system is too complex to obtain the knowledge of experts sufficiently. Therefore, automatic design of the rules from input-ou... View full abstract»

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