By Topic

Neural Networks, 1997. Proceedings., IVth Brazilian Symposium on

Date 3-5 Dec. 1997

Filter Results

Displaying Results 1 - 11 of 11
  • Proceedings 4th Brazilian Symposium on Neural Networks

    Publication Year: 1997
    Request permission for commercial reuse | PDF file iconPDF (123 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 1997, Page(s): 73
    Request permission for commercial reuse | PDF file iconPDF (28 KB)
    Freely Available from IEEE
  • An artificial neural network-genetic based approach for time series forecasting

    Publication Year: 1997, Page(s):9 - 13
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    Genetic algorithms (GAs) are a class of general optimization procedures randomized optimization heuristics based loosely on the biological paradigm of natural evolution. Artificial neural networks (ANNs) are well established optimization procedures in the domains of pattern recognition and function approximation, whose properties and training methods have been well studied. Recently there has been... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of the cascade-correlation architecture in pattern recognition applications

    Publication Year: 1997, Page(s):31 - 40
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (836 KB)

    In this work, an experimental evaluation of the cascade-correlation architecture is carried out in different benchmarking pattern recognition problems. An extensive experimental framework is developed to establish a comparison between the cascade-correlation network (CC) and the more traditional multilayer perceptron (MLP) and radial basis function models (RBF). The different network configuration... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On limited fan-in optimal neural networks

    Publication Year: 1997, Page(s):19 - 30
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1076 KB)

    This paper analyses the influence of limited fan-in on the size and VLSI optimality of highly interconnected nets. Two different approaches show that VLSI- and size-optimal discrete neural networks can be obtained for small fan-in values. They have applications to hardware implementations of neural networks. The first approach is based on implementing a certain sub-class of Boolean functions, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the information storage of associative matrix memories

    Publication Year: 1997, Page(s):51 - 57
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    This paper aims at providing insights onto fundamental properties of two of the earlier models of matrix memories: nonlinear or Willshaw's matrix model, and the linear matrix memory. These are traditional models of artificial neural networks (ANNs) on which little has been done in recent years on themes such as retrieval and storage properties, which are studied in this paper. Equations for predic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stability analysis of pRAM reinforcement learning

    Publication Year: 1997, Page(s):41 - 50
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (836 KB)

    Generalisation has been a major issue in RAM-based neural networks. In pRAM networks generalisation is produced by noisy reinforcement learning-a completely hardware implementable (built-in) algorithm. This paper presents the first part of a modular technique to analyse the formation of the basins of attraction in such systems. It proves that reinforcement learning in a single pRAM site is a globa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fingerprint classification with neural networks

    Publication Year: 1997, Page(s):66 - 72
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (752 KB)

    This paper presents some intermediate results on fingerprint classification adopting a neural network as decision stage, in order to evaluate the performance of a discrete wavelet transform as feature extraction technique. Some issues on the image acquisition, preprocessing and segmentation are also discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • UB1 - a recurrent neural network based parallel machine for solving simultaneous linear equations

    Publication Year: 1997, Page(s):14 - 18
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (324 KB)

    This paper describe the electronic realization of a recently proposed recurrent neural network for solving simultaneous linear equations which can be found in many mathematical model formulations. In many large-scale problems, the number of unknowns involved is very large. These large-scale problems often need to be solved in real-time. In this study, a systolic array is proposed that provides lin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A structured approach to neural networks in bankruptcy prediction

    Publication Year: 1997, Page(s):1 - 8
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    This paper explores the difficulties as well as a structured approach in developing neural networks in management, more specifically in bankruptcy prediction. It distinguishes the potential strategic interest in using neural networks in a firm as a decision support tool. Neural networks are developed and tested through the exploring of the French industry of merchandise transportation. Through the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolutionary design of MLP neural network architectures

    Publication Year: 1997, Page(s):58 - 65
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB)

    In neural networks design, some parameters must be adequately set for an efficient performance to be achieved. The setting of these parameters is not a trivial task since different applications may require different values. The “trial-and-error” or traditional engineering approaches for this task do not guarantee that an optimal set of parameters is found. Evolutionary approaches have ... View full abstract»

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